Datasets:

ftopal

/

huggingface-models

like 0

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

ferrazzipietro/LS_Llama-2-7b-hf_adapters_en.layer1_NoQuant_16_32_0.05_8_5e-05

2024-05-03T15:06:30+00:00

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

cilantro9246/faxebch

2024-05-03T15:06:40+00:00

TAGS #transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # rloo_zephyr_vllm11 This model was trained from scratch on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-06 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 7 - gradient_accumulation_steps: 32 - total_train_batch_size: 224 - total_eval_batch_size: 56 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.19.1

{"tags": ["generated_from_trainer"], "model-index": [{"name": "rloo_zephyr_vllm11", "results": []}]}

vwxyzjn/rloo_zephyr_vllm11

2024-05-03T15:07:17+00:00

TAGS #transformers #safetensors #mistral #text-generation #generated_from_trainer #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# rloo_zephyr_vllm11 This model was trained from scratch on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-06 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 7 - gradient_accumulation_steps: 32 - total_train_batch_size: 224 - total_eval_batch_size: 56 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.19.1

transformers

# Uploaded model - **Developed by:** animaRegem - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"}

animaRegem/llama-3-lora-01-malayalam

2024-05-03T15:07:34+00:00

TAGS #transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us

# Uploaded model - Developed by: animaRegem - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": ["unsloth"]}

animaRegem/llama-3-lora-01-malayalam-tokenizer

2024-05-03T15:07:47+00:00

TAGS #transformers #unsloth #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # segformer-b0-scene-parse-150 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the scene_parse_150 dataset. It achieves the following results on the evaluation set: - eval_loss: 2.4563 - eval_mean_iou: 0.0432 - eval_mean_accuracy: 0.0696 - eval_overall_accuracy: 0.5913 - eval_per_category_iou: [0.4472851919015029, 0.6612097108758626, 0.817339666449671, 0.47928449607416507, 0.5911507360971395, 0.584974453286796, 0.6726074613245039, 0.2589327338580983, 0.022897061669389426, 0.3531389341071555, 0.0009033242331780954, 0.0, 0.38016586218727527, 0.0065494844799213895, 3.5410365901749114e-05, 0.0006227857923162527, 0.1369807957501803, 0.0, 0.0, 0.0, 0.3866305742675126, 0.0, 0.0, 0.0, 0.0, 0.0, 0.15958629131507837, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0] - eval_per_category_accuracy: [0.8334025427555467, 0.90546175118556, 0.9576760329344776, 0.9040202679951341, 0.9084813897020947, 0.7543100790506285, 0.924642649916285, 0.6768858942434451, 0.024248627368742136, 0.8855665819147363, 0.0009169818241372258, 0.0, 0.7872266396753254, 0.006739498091427447, 3.561201678944719e-05, 0.0006261997885292518, 0.24443709595222143, 0.0, 0.0, 0.0, 0.6322151772008276, 0.0, 0.0, 0.0, 0.0, 0.0, 0.16159973151359214, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0] - eval_runtime: 22.5623 - eval_samples_per_second: 8.864 - eval_steps_per_second: 0.576 - epoch: 4.8 - step: 240 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "other", "tags": ["generated_from_trainer"], "datasets": ["scene_parse_150"], "base_model": "nvidia/mit-b0", "model-index": [{"name": "segformer-b0-scene-parse-150", "results": []}]}

ChayawatP/segformer-b0-scene-parse-150

2024-05-03T15:07:57+00:00

TAGS #transformers #tensorboard #safetensors #segformer #generated_from_trainer #dataset-scene_parse_150 #base_model-nvidia/mit-b0 #license-other #endpoints_compatible #region-us

# segformer-b0-scene-parse-150 This model is a fine-tuned version of nvidia/mit-b0 on the scene_parse_150 dataset. It achieves the following results on the evaluation set: - eval_loss: 2.4563 - eval_mean_iou: 0.0432 - eval_mean_accuracy: 0.0696 - eval_overall_accuracy: 0.5913 - eval_per_category_iou: [0.4472851919015029, 0.6612097108758626, 0.817339666449671, 0.47928449607416507, 0.5911507360971395, 0.584974453286796, 0.6726074613245039, 0.2589327338580983, 0.022897061669389426, 0.3531389341071555, 0.0009033242331780954, 0.0, 0.38016586218727527, 0.0065494844799213895, 3.5410365901749114e-05, 0.0006227857923162527, 0.1369807957501803, 0.0, 0.0, 0.0, 0.3866305742675126, 0.0, 0.0, 0.0, 0.0, 0.0, 0.15958629131507837, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0] - eval_per_category_accuracy: [0.8334025427555467, 0.90546175118556, 0.9576760329344776, 0.9040202679951341, 0.9084813897020947, 0.7543100790506285, 0.924642649916285, 0.6768858942434451, 0.024248627368742136, 0.8855665819147363, 0.0009169818241372258, 0.0, 0.7872266396753254, 0.006739498091427447, 3.561201678944719e-05, 0.0006261997885292518, 0.24443709595222143, 0.0, 0.0, 0.0, 0.6322151772008276, 0.0, 0.0, 0.0, 0.0, 0.0, 0.16159973151359214, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0] - eval_runtime: 22.5623 - eval_samples_per_second: 8.864 - eval_steps_per_second: 0.576 - epoch: 4.8 - step: 240 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 50 ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_tata-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4666 - F1 Score: 0.8026 - Accuracy: 0.8026 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5548 | 5.13 | 200 | 0.5050 | 0.7516 | 0.7553 | | 0.4582 | 10.26 | 400 | 0.4638 | 0.7994 | 0.7993 | | 0.4275 | 15.38 | 600 | 0.4521 | 0.8060 | 0.8059 | | 0.4017 | 20.51 | 800 | 0.4511 | 0.7995 | 0.7993 | | 0.3843 | 25.64 | 1000 | 0.4591 | 0.7995 | 0.7993 | | 0.3641 | 30.77 | 1200 | 0.4585 | 0.8107 | 0.8108 | | 0.3522 | 35.9 | 1400 | 0.4668 | 0.8043 | 0.8042 | | 0.3365 | 41.03 | 1600 | 0.4775 | 0.8086 | 0.8091 | | 0.3228 | 46.15 | 1800 | 0.4857 | 0.7962 | 0.7961 | | 0.3121 | 51.28 | 2000 | 0.4890 | 0.8056 | 0.8059 | | 0.303 | 56.41 | 2200 | 0.5310 | 0.7911 | 0.7912 | | 0.2937 | 61.54 | 2400 | 0.5404 | 0.7959 | 0.7961 | | 0.283 | 66.67 | 2600 | 0.5231 | 0.8076 | 0.8075 | | 0.2758 | 71.79 | 2800 | 0.5463 | 0.8026 | 0.8026 | | 0.2732 | 76.92 | 3000 | 0.5306 | 0.7960 | 0.7961 | | 0.2621 | 82.05 | 3200 | 0.5515 | 0.8059 | 0.8059 | | 0.2568 | 87.18 | 3400 | 0.5725 | 0.7977 | 0.7977 | | 0.248 | 92.31 | 3600 | 0.5643 | 0.8060 | 0.8059 | | 0.246 | 97.44 | 3800 | 0.5643 | 0.7942 | 0.7945 | | 0.2372 | 102.56 | 4000 | 0.6019 | 0.7928 | 0.7928 | | 0.2343 | 107.69 | 4200 | 0.5971 | 0.8010 | 0.8010 | | 0.2237 | 112.82 | 4400 | 0.6042 | 0.7962 | 0.7961 | | 0.2207 | 117.95 | 4600 | 0.6285 | 0.7943 | 0.7945 | | 0.2145 | 123.08 | 4800 | 0.6262 | 0.7848 | 0.7847 | | 0.21 | 128.21 | 5000 | 0.6390 | 0.7962 | 0.7961 | | 0.2078 | 133.33 | 5200 | 0.6459 | 0.7897 | 0.7896 | | 0.1989 | 138.46 | 5400 | 0.6421 | 0.7896 | 0.7896 | | 0.1996 | 143.59 | 5600 | 0.6495 | 0.7946 | 0.7945 | | 0.1968 | 148.72 | 5800 | 0.6572 | 0.8011 | 0.8010 | | 0.1925 | 153.85 | 6000 | 0.6692 | 0.8044 | 0.8042 | | 0.1917 | 158.97 | 6200 | 0.6786 | 0.7994 | 0.7993 | | 0.1868 | 164.1 | 6400 | 0.6769 | 0.7995 | 0.7993 | | 0.1846 | 169.23 | 6600 | 0.6911 | 0.7978 | 0.7977 | | 0.1786 | 174.36 | 6800 | 0.6737 | 0.7946 | 0.7945 | | 0.1803 | 179.49 | 7000 | 0.6817 | 0.7995 | 0.7993 | | 0.1777 | 184.62 | 7200 | 0.6831 | 0.7962 | 0.7961 | | 0.1745 | 189.74 | 7400 | 0.7034 | 0.7995 | 0.7993 | | 0.1752 | 194.87 | 7600 | 0.7135 | 0.7896 | 0.7896 | | 0.1703 | 200.0 | 7800 | 0.7156 | 0.7978 | 0.7977 | | 0.1649 | 205.13 | 8000 | 0.7408 | 0.7962 | 0.7961 | | 0.1744 | 210.26 | 8200 | 0.7215 | 0.7946 | 0.7945 | | 0.1698 | 215.38 | 8400 | 0.7257 | 0.7978 | 0.7977 | | 0.1637 | 220.51 | 8600 | 0.7321 | 0.7979 | 0.7977 | | 0.1608 | 225.64 | 8800 | 0.7433 | 0.7979 | 0.7977 | | 0.1613 | 230.77 | 9000 | 0.7391 | 0.8011 | 0.8010 | | 0.1636 | 235.9 | 9200 | 0.7425 | 0.7962 | 0.7961 | | 0.1573 | 241.03 | 9400 | 0.7449 | 0.7979 | 0.7977 | | 0.1632 | 246.15 | 9600 | 0.7407 | 0.7995 | 0.7993 | | 0.1612 | 251.28 | 9800 | 0.7437 | 0.7978 | 0.7977 | | 0.1601 | 256.41 | 10000 | 0.7429 | 0.7978 | 0.7977 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_65536_512_47M-L8_f

2024-05-03T15:08:13+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_300\_tata-seqsight\_65536\_512\_47M-L8\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4666 * F1 Score: 0.8026 * Accuracy: 0.8026 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_tata-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.5055 - F1 Score: 0.8041 - Accuracy: 0.8042 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5307 | 5.13 | 200 | 0.4727 | 0.7787 | 0.7798 | | 0.4297 | 10.26 | 400 | 0.4684 | 0.7909 | 0.7912 | | 0.3842 | 15.38 | 600 | 0.4664 | 0.8026 | 0.8026 | | 0.3458 | 20.51 | 800 | 0.4781 | 0.8040 | 0.8042 | | 0.3183 | 25.64 | 1000 | 0.5174 | 0.8060 | 0.8059 | | 0.2872 | 30.77 | 1200 | 0.5517 | 0.7946 | 0.7945 | | 0.2632 | 35.9 | 1400 | 0.5920 | 0.7912 | 0.7912 | | 0.2357 | 41.03 | 1600 | 0.6452 | 0.7859 | 0.7863 | | 0.2121 | 46.15 | 1800 | 0.7001 | 0.7662 | 0.7667 | | 0.1907 | 51.28 | 2000 | 0.7603 | 0.7797 | 0.7798 | | 0.1756 | 56.41 | 2200 | 0.7975 | 0.7782 | 0.7781 | | 0.1654 | 61.54 | 2400 | 0.8281 | 0.7765 | 0.7765 | | 0.1525 | 66.67 | 2600 | 0.7975 | 0.7831 | 0.7830 | | 0.1402 | 71.79 | 2800 | 0.8550 | 0.7848 | 0.7847 | | 0.1315 | 76.92 | 3000 | 0.8706 | 0.7897 | 0.7896 | | 0.1204 | 82.05 | 3200 | 0.9344 | 0.7881 | 0.7879 | | 0.1086 | 87.18 | 3400 | 0.9829 | 0.7832 | 0.7830 | | 0.1055 | 92.31 | 3600 | 1.0072 | 0.7927 | 0.7928 | | 0.1014 | 97.44 | 3800 | 0.9490 | 0.7798 | 0.7798 | | 0.0915 | 102.56 | 4000 | 1.0467 | 0.7864 | 0.7863 | | 0.0915 | 107.69 | 4200 | 1.0706 | 0.7848 | 0.7847 | | 0.0867 | 112.82 | 4400 | 1.0829 | 0.7832 | 0.7830 | | 0.0787 | 117.95 | 4600 | 1.1589 | 0.7864 | 0.7863 | | 0.0776 | 123.08 | 4800 | 1.1396 | 0.7783 | 0.7781 | | 0.0732 | 128.21 | 5000 | 1.1038 | 0.7864 | 0.7863 | | 0.0689 | 133.33 | 5200 | 1.1479 | 0.7832 | 0.7830 | | 0.0692 | 138.46 | 5400 | 1.1645 | 0.7734 | 0.7732 | | 0.0674 | 143.59 | 5600 | 1.1893 | 0.7815 | 0.7814 | | 0.0658 | 148.72 | 5800 | 1.1625 | 0.7749 | 0.7749 | | 0.0617 | 153.85 | 6000 | 1.2137 | 0.7815 | 0.7814 | | 0.0606 | 158.97 | 6200 | 1.2414 | 0.7799 | 0.7798 | | 0.056 | 164.1 | 6400 | 1.2492 | 0.7782 | 0.7781 | | 0.0598 | 169.23 | 6600 | 1.2057 | 0.7815 | 0.7814 | | 0.0553 | 174.36 | 6800 | 1.2501 | 0.7798 | 0.7798 | | 0.0533 | 179.49 | 7000 | 1.2808 | 0.7767 | 0.7765 | | 0.0532 | 184.62 | 7200 | 1.2510 | 0.7880 | 0.7879 | | 0.0531 | 189.74 | 7400 | 1.2596 | 0.7799 | 0.7798 | | 0.0514 | 194.87 | 7600 | 1.2814 | 0.7816 | 0.7814 | | 0.0496 | 200.0 | 7800 | 1.2637 | 0.7864 | 0.7863 | | 0.0463 | 205.13 | 8000 | 1.3075 | 0.7799 | 0.7798 | | 0.0493 | 210.26 | 8200 | 1.3099 | 0.7816 | 0.7814 | | 0.0471 | 215.38 | 8400 | 1.3130 | 0.7767 | 0.7765 | | 0.0433 | 220.51 | 8600 | 1.3321 | 0.7799 | 0.7798 | | 0.0442 | 225.64 | 8800 | 1.3315 | 0.7815 | 0.7814 | | 0.0437 | 230.77 | 9000 | 1.3364 | 0.7766 | 0.7765 | | 0.0431 | 235.9 | 9200 | 1.3456 | 0.7734 | 0.7732 | | 0.0429 | 241.03 | 9400 | 1.3446 | 0.7799 | 0.7798 | | 0.0439 | 246.15 | 9600 | 1.3338 | 0.7783 | 0.7781 | | 0.0462 | 251.28 | 9800 | 1.3291 | 0.7815 | 0.7814 | | 0.0418 | 256.41 | 10000 | 1.3333 | 0.7832 | 0.7830 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_65536_512_47M-L32_f

2024-05-03T15:09:08+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_300\_tata-seqsight\_65536\_512\_47M-L32\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.5055 * F1 Score: 0.8041 * Accuracy: 0.8042 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_notata-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1327 - F1 Score: 0.9504 - Accuracy: 0.9504 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.3429 | 0.6 | 200 | 0.1803 | 0.9252 | 0.9252 | | 0.1949 | 1.2 | 400 | 0.1537 | 0.9382 | 0.9382 | | 0.1793 | 1.81 | 600 | 0.1431 | 0.9420 | 0.9420 | | 0.168 | 2.41 | 800 | 0.1371 | 0.9440 | 0.9440 | | 0.1618 | 3.01 | 1000 | 0.1396 | 0.9450 | 0.9450 | | 0.1581 | 3.61 | 1200 | 0.1325 | 0.9471 | 0.9471 | | 0.16 | 4.22 | 1400 | 0.1401 | 0.9446 | 0.9446 | | 0.1499 | 4.82 | 1600 | 0.1287 | 0.9482 | 0.9482 | | 0.152 | 5.42 | 1800 | 0.1407 | 0.9452 | 0.9452 | | 0.1425 | 6.02 | 2000 | 0.1363 | 0.9474 | 0.9474 | | 0.1462 | 6.63 | 2200 | 0.1221 | 0.9536 | 0.9536 | | 0.1439 | 7.23 | 2400 | 0.1228 | 0.9508 | 0.9508 | | 0.1375 | 7.83 | 2600 | 0.1223 | 0.9529 | 0.9529 | | 0.1404 | 8.43 | 2800 | 0.1228 | 0.9521 | 0.9521 | | 0.1427 | 9.04 | 3000 | 0.1190 | 0.9517 | 0.9518 | | 0.1372 | 9.64 | 3200 | 0.1286 | 0.9510 | 0.9510 | | 0.1378 | 10.24 | 3400 | 0.1184 | 0.9531 | 0.9531 | | 0.1384 | 10.84 | 3600 | 0.1172 | 0.9536 | 0.9536 | | 0.1333 | 11.45 | 3800 | 0.1242 | 0.9516 | 0.9516 | | 0.1343 | 12.05 | 4000 | 0.1176 | 0.9563 | 0.9563 | | 0.136 | 12.65 | 4200 | 0.1175 | 0.9544 | 0.9544 | | 0.1362 | 13.25 | 4400 | 0.1166 | 0.9552 | 0.9552 | | 0.1319 | 13.86 | 4600 | 0.1147 | 0.9548 | 0.9548 | | 0.1312 | 14.46 | 4800 | 0.1158 | 0.9544 | 0.9544 | | 0.1284 | 15.06 | 5000 | 0.1158 | 0.9538 | 0.9538 | | 0.1296 | 15.66 | 5200 | 0.1147 | 0.9557 | 0.9557 | | 0.1309 | 16.27 | 5400 | 0.1136 | 0.9533 | 0.9533 | | 0.1228 | 16.87 | 5600 | 0.1137 | 0.9540 | 0.9540 | | 0.1289 | 17.47 | 5800 | 0.1125 | 0.9546 | 0.9546 | | 0.131 | 18.07 | 6000 | 0.1135 | 0.9552 | 0.9552 | | 0.1287 | 18.67 | 6200 | 0.1125 | 0.9542 | 0.9542 | | 0.1292 | 19.28 | 6400 | 0.1122 | 0.9535 | 0.9535 | | 0.1254 | 19.88 | 6600 | 0.1129 | 0.9534 | 0.9535 | | 0.1302 | 20.48 | 6800 | 0.1116 | 0.9553 | 0.9553 | | 0.1223 | 21.08 | 7000 | 0.1126 | 0.9557 | 0.9557 | | 0.1245 | 21.69 | 7200 | 0.1152 | 0.9553 | 0.9553 | | 0.1258 | 22.29 | 7400 | 0.1138 | 0.9565 | 0.9565 | | 0.1279 | 22.89 | 7600 | 0.1118 | 0.9565 | 0.9565 | | 0.1227 | 23.49 | 7800 | 0.1128 | 0.9559 | 0.9559 | | 0.1237 | 24.1 | 8000 | 0.1122 | 0.9548 | 0.9548 | | 0.1256 | 24.7 | 8200 | 0.1112 | 0.9546 | 0.9546 | | 0.1238 | 25.3 | 8400 | 0.1098 | 0.9544 | 0.9544 | | 0.1252 | 25.9 | 8600 | 0.1113 | 0.9567 | 0.9567 | | 0.1233 | 26.51 | 8800 | 0.1109 | 0.9557 | 0.9557 | | 0.1253 | 27.11 | 9000 | 0.1102 | 0.9548 | 0.9548 | | 0.1222 | 27.71 | 9200 | 0.1104 | 0.9555 | 0.9555 | | 0.1192 | 28.31 | 9400 | 0.1105 | 0.9555 | 0.9555 | | 0.1282 | 28.92 | 9600 | 0.1108 | 0.9563 | 0.9563 | | 0.1206 | 29.52 | 9800 | 0.1107 | 0.9552 | 0.9552 | | 0.1229 | 30.12 | 10000 | 0.1106 | 0.9555 | 0.9555 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_65536_512_47M-L1_f

2024-05-03T15:09:09+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_300\_notata-seqsight\_65536\_512\_47M-L1\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1327 * F1 Score: 0.9504 * Accuracy: 0.9504 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct DPO fine tuning method using the following datasets: - https://huggingface.co/datasets/Intel/orca_dpo_pairs - https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo - https://huggingface.co/datasets/unalignment/toxic-dpo-v0.2 - https://huggingface.co/datasets/M4-ai/prm_dpo_pairs_cleaned - https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1 We are happy for anyone to try it out and give some feedback and we will have the model up on https://awanllm.com on our LLM API if it is popular. Instruct format: ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|> {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|> {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> ``` Quants: FP16: https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Instruct-DPO-v0.1 GGUF: https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF

{"license": "llama3"}

AwanLLM/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF

2024-05-03T15:09:21+00:00

TAGS #gguf #license-llama3 #region-us

Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: URL DPO fine tuning method using the following datasets: - URL - URL - URL - URL - URL We are happy for anyone to try it out and give some feedback and we will have the model up on URL on our LLM API if it is popular. Instruct format: Quants: FP16: URL GGUF: URL

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

GamblerOnTrain/SSNI-367

2024-05-03T15:09:39+00:00

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

GamblerOnTrain/SDNM-448

2024-05-03T15:09:42+00:00

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_notata-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1188 - F1 Score: 0.9561 - Accuracy: 0.9561 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.2673 | 0.6 | 200 | 0.1413 | 0.9446 | 0.9446 | | 0.1534 | 1.2 | 400 | 0.1216 | 0.9531 | 0.9531 | | 0.1432 | 1.81 | 600 | 0.1169 | 0.9540 | 0.9540 | | 0.1285 | 2.41 | 800 | 0.1113 | 0.9548 | 0.9548 | | 0.1276 | 3.01 | 1000 | 0.1150 | 0.9550 | 0.9550 | | 0.123 | 3.61 | 1200 | 0.1117 | 0.9549 | 0.9550 | | 0.1236 | 4.22 | 1400 | 0.1043 | 0.9568 | 0.9568 | | 0.1175 | 4.82 | 1600 | 0.1039 | 0.9587 | 0.9587 | | 0.1194 | 5.42 | 1800 | 0.1027 | 0.9583 | 0.9584 | | 0.1102 | 6.02 | 2000 | 0.1048 | 0.9580 | 0.9580 | | 0.1133 | 6.63 | 2200 | 0.1019 | 0.9606 | 0.9606 | | 0.108 | 7.23 | 2400 | 0.1015 | 0.9614 | 0.9614 | | 0.1044 | 7.83 | 2600 | 0.1025 | 0.9608 | 0.9608 | | 0.1069 | 8.43 | 2800 | 0.1215 | 0.9548 | 0.9548 | | 0.1088 | 9.04 | 3000 | 0.1005 | 0.9612 | 0.9612 | | 0.1034 | 9.64 | 3200 | 0.1039 | 0.9593 | 0.9593 | | 0.1027 | 10.24 | 3400 | 0.0999 | 0.9610 | 0.9610 | | 0.104 | 10.84 | 3600 | 0.0982 | 0.9604 | 0.9604 | | 0.0961 | 11.45 | 3800 | 0.1007 | 0.9608 | 0.9608 | | 0.0969 | 12.05 | 4000 | 0.1006 | 0.9619 | 0.9619 | | 0.0976 | 12.65 | 4200 | 0.0973 | 0.9616 | 0.9616 | | 0.0979 | 13.25 | 4400 | 0.1016 | 0.9606 | 0.9606 | | 0.0929 | 13.86 | 4600 | 0.0961 | 0.9614 | 0.9614 | | 0.0915 | 14.46 | 4800 | 0.1039 | 0.9612 | 0.9612 | | 0.0935 | 15.06 | 5000 | 0.1010 | 0.9595 | 0.9595 | | 0.0906 | 15.66 | 5200 | 0.0977 | 0.9621 | 0.9621 | | 0.0909 | 16.27 | 5400 | 0.1007 | 0.9616 | 0.9616 | | 0.0862 | 16.87 | 5600 | 0.1006 | 0.9604 | 0.9604 | | 0.088 | 17.47 | 5800 | 0.0983 | 0.9614 | 0.9614 | | 0.0917 | 18.07 | 6000 | 0.0972 | 0.9625 | 0.9625 | | 0.0871 | 18.67 | 6200 | 0.0982 | 0.9634 | 0.9634 | | 0.0876 | 19.28 | 6400 | 0.1016 | 0.9606 | 0.9606 | | 0.0838 | 19.88 | 6600 | 0.1026 | 0.9617 | 0.9617 | | 0.0886 | 20.48 | 6800 | 0.1015 | 0.9616 | 0.9616 | | 0.0809 | 21.08 | 7000 | 0.1023 | 0.9606 | 0.9606 | | 0.0844 | 21.69 | 7200 | 0.1022 | 0.9616 | 0.9616 | | 0.0818 | 22.29 | 7400 | 0.1043 | 0.9601 | 0.9601 | | 0.0837 | 22.89 | 7600 | 0.1006 | 0.9612 | 0.9612 | | 0.0797 | 23.49 | 7800 | 0.1030 | 0.9621 | 0.9621 | | 0.0802 | 24.1 | 8000 | 0.1003 | 0.9629 | 0.9629 | | 0.0803 | 24.7 | 8200 | 0.1018 | 0.9621 | 0.9621 | | 0.0791 | 25.3 | 8400 | 0.1009 | 0.9617 | 0.9617 | | 0.0789 | 25.9 | 8600 | 0.1010 | 0.9631 | 0.9631 | | 0.0802 | 26.51 | 8800 | 0.1020 | 0.9614 | 0.9614 | | 0.0791 | 27.11 | 9000 | 0.0996 | 0.9623 | 0.9623 | | 0.0772 | 27.71 | 9200 | 0.1006 | 0.9623 | 0.9623 | | 0.075 | 28.31 | 9400 | 0.1024 | 0.9621 | 0.9621 | | 0.0812 | 28.92 | 9600 | 0.1016 | 0.9621 | 0.9621 | | 0.074 | 29.52 | 9800 | 0.1017 | 0.9617 | 0.9617 | | 0.078 | 30.12 | 10000 | 0.1013 | 0.9623 | 0.9623 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_65536_512_47M-L32_f

2024-05-03T15:10:00+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_300\_notata-seqsight\_65536\_512\_47M-L32\_f ============================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1188 * F1 Score: 0.9561 * Accuracy: 0.9561 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_notata-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1215 - F1 Score: 0.9536 - Accuracy: 0.9536 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.2907 | 0.6 | 200 | 0.1476 | 0.9401 | 0.9401 | | 0.1704 | 1.2 | 400 | 0.1310 | 0.9500 | 0.9501 | | 0.1551 | 1.81 | 600 | 0.1234 | 0.9518 | 0.9518 | | 0.1386 | 2.41 | 800 | 0.1177 | 0.9527 | 0.9527 | | 0.1356 | 3.01 | 1000 | 0.1208 | 0.9533 | 0.9533 | | 0.1322 | 3.61 | 1200 | 0.1136 | 0.9538 | 0.9538 | | 0.1342 | 4.22 | 1400 | 0.1152 | 0.9548 | 0.9548 | | 0.1255 | 4.82 | 1600 | 0.1090 | 0.9570 | 0.9570 | | 0.1286 | 5.42 | 1800 | 0.1090 | 0.9563 | 0.9563 | | 0.1202 | 6.02 | 2000 | 0.1089 | 0.9569 | 0.9568 | | 0.1233 | 6.63 | 2200 | 0.1050 | 0.9578 | 0.9578 | | 0.1185 | 7.23 | 2400 | 0.1058 | 0.9585 | 0.9585 | | 0.115 | 7.83 | 2600 | 0.1066 | 0.9585 | 0.9585 | | 0.1179 | 8.43 | 2800 | 0.1076 | 0.9567 | 0.9567 | | 0.1208 | 9.04 | 3000 | 0.1067 | 0.9566 | 0.9567 | | 0.1145 | 9.64 | 3200 | 0.1089 | 0.9584 | 0.9584 | | 0.116 | 10.24 | 3400 | 0.1037 | 0.9602 | 0.9602 | | 0.1157 | 10.84 | 3600 | 0.1020 | 0.9587 | 0.9587 | | 0.1103 | 11.45 | 3800 | 0.1030 | 0.9570 | 0.9570 | | 0.1111 | 12.05 | 4000 | 0.1031 | 0.9585 | 0.9585 | | 0.113 | 12.65 | 4200 | 0.1007 | 0.9593 | 0.9593 | | 0.1121 | 13.25 | 4400 | 0.1026 | 0.9582 | 0.9582 | | 0.1088 | 13.86 | 4600 | 0.1006 | 0.9585 | 0.9585 | | 0.1087 | 14.46 | 4800 | 0.1022 | 0.9584 | 0.9584 | | 0.1068 | 15.06 | 5000 | 0.1024 | 0.9572 | 0.9572 | | 0.1061 | 15.66 | 5200 | 0.1008 | 0.9585 | 0.9585 | | 0.1079 | 16.27 | 5400 | 0.1027 | 0.9593 | 0.9593 | | 0.1017 | 16.87 | 5600 | 0.1010 | 0.9597 | 0.9597 | | 0.1065 | 17.47 | 5800 | 0.0994 | 0.9600 | 0.9601 | | 0.1092 | 18.07 | 6000 | 0.0988 | 0.9600 | 0.9601 | | 0.1059 | 18.67 | 6200 | 0.0993 | 0.9606 | 0.9606 | | 0.1059 | 19.28 | 6400 | 0.1002 | 0.9608 | 0.9608 | | 0.102 | 19.88 | 6600 | 0.1012 | 0.9610 | 0.9610 | | 0.1073 | 20.48 | 6800 | 0.1008 | 0.9595 | 0.9595 | | 0.0999 | 21.08 | 7000 | 0.0996 | 0.9600 | 0.9601 | | 0.1031 | 21.69 | 7200 | 0.1016 | 0.9595 | 0.9595 | | 0.1025 | 22.29 | 7400 | 0.1003 | 0.9593 | 0.9593 | | 0.1042 | 22.89 | 7600 | 0.0990 | 0.9599 | 0.9599 | | 0.1001 | 23.49 | 7800 | 0.0998 | 0.9599 | 0.9599 | | 0.1021 | 24.1 | 8000 | 0.0995 | 0.9608 | 0.9608 | | 0.1017 | 24.7 | 8200 | 0.0989 | 0.9606 | 0.9606 | | 0.1015 | 25.3 | 8400 | 0.0985 | 0.9608 | 0.9608 | | 0.1007 | 25.9 | 8600 | 0.0991 | 0.9608 | 0.9608 | | 0.1007 | 26.51 | 8800 | 0.0989 | 0.9610 | 0.9610 | | 0.1012 | 27.11 | 9000 | 0.0982 | 0.9606 | 0.9606 | | 0.0987 | 27.71 | 9200 | 0.0984 | 0.9608 | 0.9608 | | 0.0965 | 28.31 | 9400 | 0.0987 | 0.9606 | 0.9606 | | 0.1031 | 28.92 | 9600 | 0.0987 | 0.9606 | 0.9606 | | 0.0962 | 29.52 | 9800 | 0.0985 | 0.9602 | 0.9602 | | 0.0993 | 30.12 | 10000 | 0.0984 | 0.9606 | 0.9606 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_65536_512_47M-L8_f

2024-05-03T15:10:00+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_300\_notata-seqsight\_65536\_512\_47M-L8\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1215 * F1 Score: 0.9536 * Accuracy: 0.9536 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # falcon7binstruct_mentalhealthmodel_oct23 This model is a fine-tuned version of [vilsonrodrigues/falcon-7b-instruct-sharded](https://huggingface.co/vilsonrodrigues/falcon-7b-instruct-sharded) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.03 - training_steps: 180 ### Training results ### Framework versions - Transformers 4.32.1 - Pytorch 2.3.0+cu118 - Datasets 2.19.0 - Tokenizers 0.13.2

{"license": "apache-2.0", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "vilsonrodrigues/falcon-7b-instruct-sharded", "model-index": [{"name": "falcon7binstruct_mentalhealthmodel_oct23", "results": []}]}

KingMidas89/falcon7binstruct_mentalhealthmodel_oct23

2024-05-03T15:10:42+00:00

TAGS #trl #sft #generated_from_trainer #base_model-vilsonrodrigues/falcon-7b-instruct-sharded #license-apache-2.0 #region-us

# falcon7binstruct_mentalhealthmodel_oct23 This model is a fine-tuned version of vilsonrodrigues/falcon-7b-instruct-sharded on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.03 - training_steps: 180 ### Training results ### Framework versions - Transformers 4.32.1 - Pytorch 2.3.0+cu118 - Datasets 2.19.0 - Tokenizers 0.13.2

transformers

# Uploaded model - **Developed by:** rvian - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"}

rvian/lora-llama3-midjourney-prompt-generator

2024-05-03T15:11:31+00:00

TAGS #transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us

# Uploaded model - Developed by: rvian - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": ["unsloth"]}

Mustfain/News-headline-Generation

2024-05-03T15:13:32+00:00

TAGS #transformers #safetensors #unsloth #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

GamblerOnTrain/SAN-235

2024-05-03T15:13:48+00:00

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

ferrazzipietro/LS_Llama-2-7b-hf_adapters_en.layer1_NoQuant_16_32_0.05_8_0.0002

2024-05-03T15:13:49+00:00

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

GamblerOnTrain/SAN-236

2024-05-03T15:13:51+00:00

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": ["unsloth"]}

mayukhbis/llama3-gguf

2024-05-03T15:14:38+00:00

TAGS #transformers #safetensors #unsloth #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # gptneo-TxtToJson-v0.3.1 This model is a fine-tuned version of [EleutherAI/gpt-neo-125m](https://huggingface.co/EleutherAI/gpt-neo-125m) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1921 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.9333 | 1.0 | 219 | 0.9018 | | 0.6128 | 2.0 | 438 | 0.5939 | | 0.3284 | 3.0 | 657 | 0.3776 | | 0.1879 | 4.0 | 876 | 0.2272 | | 0.1326 | 5.0 | 1095 | 0.1921 | ### Framework versions - Transformers 4.27.4 - Pytorch 1.13.0 - Datasets 2.1.0 - Tokenizers 0.13.2

{"license": "mit", "tags": ["generated_from_trainer"], "model-index": [{"name": "gptneo-TxtToJson-v0.3.1", "results": []}]}

AhmedTaha012/gptneo-TxtToJson-v0.3.1

2024-05-03T15:15:10+00:00

TAGS #transformers #pytorch #tensorboard #gpt_neo #text-generation #generated_from_trainer #license-mit #autotrain_compatible #endpoints_compatible #region-us

gptneo-TxtToJson-v0.3.1 ======================= This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None dataset. It achieves the following results on the evaluation set: * Loss: 0.1921 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0002 * train\_batch\_size: 2 * eval\_batch\_size: 2 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 5 ### Training results ### Framework versions * Transformers 4.27.4 * Pytorch 1.13.0 * Datasets 2.1.0 * Tokenizers 0.13.2

text-generation

transformers

# Uploaded model - **Developed by:** waylandzhang - **License:** apache-2.0 - **Finetuned from model :** Llama-3-8b-Chinese-Novel-4bit-lesson-v2 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "Llama-3-8b-Chinese-Novel-4bit-lesson-v2"}

waylandzhang/Llama-3-8b-Chinese-Novel-4bit-lesson-v2

2024-05-03T15:15:13+00:00

TAGS #transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #conversational #en #base_model-Llama-3-8b-Chinese-Novel-4bit-lesson-v2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us

# Uploaded model - Developed by: waylandzhang - License: apache-2.0 - Finetuned from model : Llama-3-8b-Chinese-Novel-4bit-lesson-v2 This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

golf2248/9x70bu1

2024-05-03T15:15:34+00:00

TAGS #transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_all-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4257 - F1 Score: 0.8007 - Accuracy: 0.8008 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.549 | 0.54 | 200 | 0.4976 | 0.7582 | 0.7595 | | 0.487 | 1.08 | 400 | 0.4718 | 0.7750 | 0.7752 | | 0.4771 | 1.62 | 600 | 0.4630 | 0.7801 | 0.7801 | | 0.4668 | 2.16 | 800 | 0.4605 | 0.7807 | 0.7807 | | 0.4679 | 2.7 | 1000 | 0.4629 | 0.7809 | 0.7812 | | 0.4644 | 3.24 | 1200 | 0.4596 | 0.7829 | 0.7833 | | 0.4585 | 3.78 | 1400 | 0.4593 | 0.7808 | 0.7812 | | 0.4543 | 4.32 | 1600 | 0.4668 | 0.7818 | 0.7826 | | 0.4524 | 4.86 | 1800 | 0.4616 | 0.7837 | 0.7843 | | 0.4524 | 5.41 | 2000 | 0.4568 | 0.7876 | 0.7880 | | 0.4494 | 5.95 | 2200 | 0.4508 | 0.7900 | 0.7900 | | 0.4502 | 6.49 | 2400 | 0.4500 | 0.7899 | 0.7900 | | 0.4417 | 7.03 | 2600 | 0.4465 | 0.7914 | 0.7914 | | 0.4475 | 7.57 | 2800 | 0.4516 | 0.7919 | 0.7921 | | 0.4415 | 8.11 | 3000 | 0.4528 | 0.7868 | 0.7873 | | 0.4412 | 8.65 | 3200 | 0.4449 | 0.7936 | 0.7936 | | 0.4447 | 9.19 | 3400 | 0.4458 | 0.7918 | 0.7919 | | 0.4368 | 9.73 | 3600 | 0.4534 | 0.7882 | 0.7889 | | 0.4416 | 10.27 | 3800 | 0.4480 | 0.7890 | 0.7894 | | 0.4402 | 10.81 | 4000 | 0.4432 | 0.7936 | 0.7936 | | 0.4403 | 11.35 | 4200 | 0.4446 | 0.7922 | 0.7924 | | 0.4375 | 11.89 | 4400 | 0.4480 | 0.7916 | 0.7921 | | 0.4358 | 12.43 | 4600 | 0.4401 | 0.7973 | 0.7973 | | 0.4337 | 12.97 | 4800 | 0.4428 | 0.7934 | 0.7936 | | 0.4349 | 13.51 | 5000 | 0.4518 | 0.7875 | 0.7885 | | 0.433 | 14.05 | 5200 | 0.4425 | 0.7932 | 0.7934 | | 0.4319 | 14.59 | 5400 | 0.4393 | 0.7973 | 0.7973 | | 0.4317 | 15.14 | 5600 | 0.4396 | 0.7976 | 0.7976 | | 0.4326 | 15.68 | 5800 | 0.4442 | 0.7919 | 0.7924 | | 0.4274 | 16.22 | 6000 | 0.4443 | 0.7920 | 0.7924 | | 0.4354 | 16.76 | 6200 | 0.4405 | 0.7941 | 0.7944 | | 0.4318 | 17.3 | 6400 | 0.4427 | 0.7921 | 0.7926 | | 0.4311 | 17.84 | 6600 | 0.4425 | 0.7918 | 0.7922 | | 0.4299 | 18.38 | 6800 | 0.4439 | 0.7905 | 0.7912 | | 0.4295 | 18.92 | 7000 | 0.4402 | 0.7951 | 0.7954 | | 0.423 | 19.46 | 7200 | 0.4400 | 0.7978 | 0.7980 | | 0.434 | 20.0 | 7400 | 0.4384 | 0.7968 | 0.7970 | | 0.4285 | 20.54 | 7600 | 0.4409 | 0.7936 | 0.7939 | | 0.4247 | 21.08 | 7800 | 0.4419 | 0.7958 | 0.7961 | | 0.4277 | 21.62 | 8000 | 0.4382 | 0.7955 | 0.7956 | | 0.4288 | 22.16 | 8200 | 0.4382 | 0.7982 | 0.7983 | | 0.4335 | 22.7 | 8400 | 0.4407 | 0.7933 | 0.7937 | | 0.4244 | 23.24 | 8600 | 0.4383 | 0.7951 | 0.7953 | | 0.4243 | 23.78 | 8800 | 0.4388 | 0.7963 | 0.7965 | | 0.4248 | 24.32 | 9000 | 0.4377 | 0.7982 | 0.7983 | | 0.4276 | 24.86 | 9200 | 0.4377 | 0.7975 | 0.7976 | | 0.4387 | 25.41 | 9400 | 0.4372 | 0.7958 | 0.7959 | | 0.4208 | 25.95 | 9600 | 0.4376 | 0.7968 | 0.7970 | | 0.4303 | 26.49 | 9800 | 0.4389 | 0.7959 | 0.7961 | | 0.4243 | 27.03 | 10000 | 0.4384 | 0.7962 | 0.7965 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_65536_512_47M-L1_f

2024-05-03T15:16:03+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_all-seqsight\_65536\_512\_47M-L1\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4257 * F1 Score: 0.8007 * Accuracy: 0.8008 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_all-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4193 - F1 Score: 0.8054 - Accuracy: 0.8056 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.526 | 0.54 | 200 | 0.4758 | 0.7691 | 0.7698 | | 0.4709 | 1.08 | 400 | 0.4679 | 0.7773 | 0.7779 | | 0.4604 | 1.62 | 600 | 0.4528 | 0.7853 | 0.7853 | | 0.4477 | 2.16 | 800 | 0.4555 | 0.7883 | 0.7885 | | 0.4485 | 2.7 | 1000 | 0.4553 | 0.7842 | 0.7850 | | 0.4449 | 3.24 | 1200 | 0.4446 | 0.7877 | 0.7880 | | 0.4387 | 3.78 | 1400 | 0.4491 | 0.7882 | 0.7890 | | 0.4322 | 4.32 | 1600 | 0.4488 | 0.7902 | 0.7909 | | 0.4316 | 4.86 | 1800 | 0.4496 | 0.7901 | 0.7909 | | 0.4319 | 5.41 | 2000 | 0.4445 | 0.7915 | 0.7921 | | 0.4288 | 5.95 | 2200 | 0.4381 | 0.7986 | 0.7986 | | 0.4292 | 6.49 | 2400 | 0.4365 | 0.7974 | 0.7975 | | 0.4201 | 7.03 | 2600 | 0.4383 | 0.7981 | 0.7981 | | 0.4242 | 7.57 | 2800 | 0.4390 | 0.7993 | 0.7993 | | 0.4205 | 8.11 | 3000 | 0.4402 | 0.7938 | 0.7944 | | 0.4195 | 8.65 | 3200 | 0.4349 | 0.7990 | 0.7992 | | 0.4236 | 9.19 | 3400 | 0.4336 | 0.8013 | 0.8014 | | 0.4177 | 9.73 | 3600 | 0.4404 | 0.7960 | 0.7965 | | 0.4211 | 10.27 | 3800 | 0.4361 | 0.7984 | 0.7986 | | 0.4178 | 10.81 | 4000 | 0.4395 | 0.7978 | 0.7978 | | 0.4184 | 11.35 | 4200 | 0.4357 | 0.8010 | 0.8012 | | 0.416 | 11.89 | 4400 | 0.4357 | 0.7957 | 0.7963 | | 0.4147 | 12.43 | 4600 | 0.4314 | 0.8011 | 0.8012 | | 0.4137 | 12.97 | 4800 | 0.4320 | 0.8023 | 0.8024 | | 0.4148 | 13.51 | 5000 | 0.4417 | 0.7896 | 0.7909 | | 0.4119 | 14.05 | 5200 | 0.4309 | 0.8016 | 0.8017 | | 0.4099 | 14.59 | 5400 | 0.4304 | 0.8017 | 0.8017 | | 0.4126 | 15.14 | 5600 | 0.4311 | 0.8008 | 0.8008 | | 0.411 | 15.68 | 5800 | 0.4394 | 0.7957 | 0.7966 | | 0.4071 | 16.22 | 6000 | 0.4338 | 0.8024 | 0.8029 | | 0.4131 | 16.76 | 6200 | 0.4273 | 0.8024 | 0.8025 | | 0.4118 | 17.3 | 6400 | 0.4299 | 0.8017 | 0.8020 | | 0.4103 | 17.84 | 6600 | 0.4301 | 0.8021 | 0.8024 | | 0.4071 | 18.38 | 6800 | 0.4381 | 0.7940 | 0.7951 | | 0.4084 | 18.92 | 7000 | 0.4289 | 0.8024 | 0.8027 | | 0.4003 | 19.46 | 7200 | 0.4300 | 0.8045 | 0.8047 | | 0.412 | 20.0 | 7400 | 0.4284 | 0.8041 | 0.8042 | | 0.4064 | 20.54 | 7600 | 0.4316 | 0.8042 | 0.8046 | | 0.4029 | 21.08 | 7800 | 0.4307 | 0.8054 | 0.8056 | | 0.4037 | 21.62 | 8000 | 0.4268 | 0.8032 | 0.8032 | | 0.4058 | 22.16 | 8200 | 0.4276 | 0.8044 | 0.8046 | | 0.4105 | 22.7 | 8400 | 0.4313 | 0.8029 | 0.8034 | | 0.401 | 23.24 | 8600 | 0.4283 | 0.8025 | 0.8027 | | 0.4021 | 23.78 | 8800 | 0.4289 | 0.8032 | 0.8034 | | 0.4006 | 24.32 | 9000 | 0.4281 | 0.8038 | 0.8039 | | 0.4035 | 24.86 | 9200 | 0.4288 | 0.8032 | 0.8034 | | 0.4139 | 25.41 | 9400 | 0.4271 | 0.8031 | 0.8032 | | 0.3975 | 25.95 | 9600 | 0.4281 | 0.8038 | 0.8039 | | 0.4074 | 26.49 | 9800 | 0.4291 | 0.8030 | 0.8032 | | 0.4027 | 27.03 | 10000 | 0.4288 | 0.8034 | 0.8035 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_65536_512_47M-L8_f

2024-05-03T15:18:45+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_all-seqsight\_65536\_512\_47M-L8\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4193 * F1 Score: 0.8054 * Accuracy: 0.8056 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_all-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4156 - F1 Score: 0.8109 - Accuracy: 0.8110 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5132 | 0.54 | 200 | 0.4606 | 0.7790 | 0.7791 | | 0.4625 | 1.08 | 400 | 0.4707 | 0.7759 | 0.7772 | | 0.4478 | 1.62 | 600 | 0.4477 | 0.7905 | 0.7907 | | 0.4355 | 2.16 | 800 | 0.4496 | 0.7915 | 0.7919 | | 0.4368 | 2.7 | 1000 | 0.4496 | 0.7880 | 0.7892 | | 0.433 | 3.24 | 1200 | 0.4341 | 0.7970 | 0.7971 | | 0.4274 | 3.78 | 1400 | 0.4410 | 0.7922 | 0.7931 | | 0.4195 | 4.32 | 1600 | 0.4366 | 0.7994 | 0.7997 | | 0.422 | 4.86 | 1800 | 0.4424 | 0.7957 | 0.7965 | | 0.42 | 5.41 | 2000 | 0.4373 | 0.7984 | 0.7990 | | 0.4181 | 5.95 | 2200 | 0.4332 | 0.8020 | 0.8020 | | 0.4171 | 6.49 | 2400 | 0.4306 | 0.8014 | 0.8015 | | 0.4083 | 7.03 | 2600 | 0.4315 | 0.8081 | 0.8081 | | 0.4111 | 7.57 | 2800 | 0.4338 | 0.8024 | 0.8024 | | 0.4086 | 8.11 | 3000 | 0.4315 | 0.8030 | 0.8034 | | 0.4062 | 8.65 | 3200 | 0.4297 | 0.8022 | 0.8025 | | 0.4087 | 9.19 | 3400 | 0.4271 | 0.8037 | 0.8037 | | 0.404 | 9.73 | 3600 | 0.4336 | 0.8026 | 0.8030 | | 0.406 | 10.27 | 3800 | 0.4313 | 0.8051 | 0.8054 | | 0.4013 | 10.81 | 4000 | 0.4364 | 0.8054 | 0.8054 | | 0.4023 | 11.35 | 4200 | 0.4277 | 0.8066 | 0.8068 | | 0.3986 | 11.89 | 4400 | 0.4297 | 0.8014 | 0.8019 | | 0.3979 | 12.43 | 4600 | 0.4287 | 0.8071 | 0.8071 | | 0.3977 | 12.97 | 4800 | 0.4271 | 0.8047 | 0.8047 | | 0.3981 | 13.51 | 5000 | 0.4321 | 0.8036 | 0.8044 | | 0.3933 | 14.05 | 5200 | 0.4248 | 0.8083 | 0.8083 | | 0.3888 | 14.59 | 5400 | 0.4270 | 0.8068 | 0.8069 | | 0.3943 | 15.14 | 5600 | 0.4270 | 0.8072 | 0.8073 | | 0.3905 | 15.68 | 5800 | 0.4352 | 0.8020 | 0.8029 | | 0.3869 | 16.22 | 6000 | 0.4285 | 0.8054 | 0.8057 | | 0.393 | 16.76 | 6200 | 0.4206 | 0.8074 | 0.8076 | | 0.3903 | 17.3 | 6400 | 0.4256 | 0.8080 | 0.8083 | | 0.3896 | 17.84 | 6600 | 0.4255 | 0.8083 | 0.8086 | | 0.3859 | 18.38 | 6800 | 0.4339 | 0.8035 | 0.8044 | | 0.3861 | 18.92 | 7000 | 0.4214 | 0.8095 | 0.8098 | | 0.3767 | 19.46 | 7200 | 0.4267 | 0.8053 | 0.8056 | | 0.3911 | 20.0 | 7400 | 0.4236 | 0.8093 | 0.8095 | | 0.3823 | 20.54 | 7600 | 0.4286 | 0.8060 | 0.8064 | | 0.3793 | 21.08 | 7800 | 0.4268 | 0.8106 | 0.8108 | | 0.3811 | 21.62 | 8000 | 0.4190 | 0.8094 | 0.8095 | | 0.3812 | 22.16 | 8200 | 0.4225 | 0.8069 | 0.8071 | | 0.3844 | 22.7 | 8400 | 0.4288 | 0.8070 | 0.8074 | | 0.3786 | 23.24 | 8600 | 0.4225 | 0.8086 | 0.8088 | | 0.3761 | 23.78 | 8800 | 0.4261 | 0.8088 | 0.8090 | | 0.3754 | 24.32 | 9000 | 0.4253 | 0.8090 | 0.8091 | | 0.3777 | 24.86 | 9200 | 0.4252 | 0.8076 | 0.8078 | | 0.3854 | 25.41 | 9400 | 0.4232 | 0.8078 | 0.8079 | | 0.3738 | 25.95 | 9600 | 0.4243 | 0.8088 | 0.8090 | | 0.3793 | 26.49 | 9800 | 0.4254 | 0.8087 | 0.8090 | | 0.3786 | 27.03 | 10000 | 0.4251 | 0.8084 | 0.8086 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_65536_512_47M-L32_f

2024-05-03T15:19:37+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_all-seqsight\_65536\_512\_47M-L32\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4156 * F1 Score: 0.8109 * Accuracy: 0.8110 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-classification

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

quangtqv/cross_encoder_tool_learning_v1

2024-05-03T15:19:56+00:00

TAGS #transformers #safetensors #xlm-roberta #text-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_notata-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3864 - F1 Score: 0.8244 - Accuracy: 0.8244 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5401 | 0.6 | 200 | 0.4229 | 0.8010 | 0.8012 | | 0.4555 | 1.2 | 400 | 0.4026 | 0.8174 | 0.8174 | | 0.4417 | 1.81 | 600 | 0.3950 | 0.8208 | 0.8208 | | 0.4392 | 2.41 | 800 | 0.3931 | 0.8234 | 0.8234 | | 0.4271 | 3.01 | 1000 | 0.3877 | 0.8263 | 0.8263 | | 0.4232 | 3.61 | 1200 | 0.3867 | 0.8320 | 0.8321 | | 0.4263 | 4.22 | 1400 | 0.3861 | 0.8296 | 0.8297 | | 0.4219 | 4.82 | 1600 | 0.3821 | 0.8308 | 0.8308 | | 0.4145 | 5.42 | 1800 | 0.3790 | 0.8338 | 0.8338 | | 0.4172 | 6.02 | 2000 | 0.3822 | 0.8308 | 0.8312 | | 0.4138 | 6.63 | 2200 | 0.3785 | 0.8304 | 0.8306 | | 0.4095 | 7.23 | 2400 | 0.3788 | 0.8330 | 0.8334 | | 0.408 | 7.83 | 2600 | 0.3765 | 0.8356 | 0.8359 | | 0.4016 | 8.43 | 2800 | 0.3857 | 0.8306 | 0.8314 | | 0.4067 | 9.04 | 3000 | 0.3784 | 0.8337 | 0.8342 | | 0.4005 | 9.64 | 3200 | 0.3701 | 0.8386 | 0.8387 | | 0.4027 | 10.24 | 3400 | 0.3698 | 0.8371 | 0.8372 | | 0.3984 | 10.84 | 3600 | 0.3687 | 0.8366 | 0.8366 | | 0.3998 | 11.45 | 3800 | 0.3714 | 0.8399 | 0.8400 | | 0.3972 | 12.05 | 4000 | 0.3693 | 0.8397 | 0.8398 | | 0.3943 | 12.65 | 4200 | 0.3703 | 0.8397 | 0.8398 | | 0.4001 | 13.25 | 4400 | 0.3704 | 0.8373 | 0.8374 | | 0.3998 | 13.86 | 4600 | 0.3683 | 0.8394 | 0.8395 | | 0.3954 | 14.46 | 4800 | 0.3684 | 0.8396 | 0.8396 | | 0.3926 | 15.06 | 5000 | 0.3705 | 0.8364 | 0.8364 | | 0.3924 | 15.66 | 5200 | 0.3683 | 0.8398 | 0.8398 | | 0.3911 | 16.27 | 5400 | 0.3681 | 0.8392 | 0.8393 | | 0.3924 | 16.87 | 5600 | 0.3793 | 0.8339 | 0.8346 | | 0.3892 | 17.47 | 5800 | 0.3756 | 0.8325 | 0.8331 | | 0.397 | 18.07 | 6000 | 0.3725 | 0.8377 | 0.8381 | | 0.3895 | 18.67 | 6200 | 0.3694 | 0.8389 | 0.8391 | | 0.3988 | 19.28 | 6400 | 0.3660 | 0.8396 | 0.8396 | | 0.3886 | 19.88 | 6600 | 0.3688 | 0.8385 | 0.8387 | | 0.3878 | 20.48 | 6800 | 0.3704 | 0.8387 | 0.8389 | | 0.3956 | 21.08 | 7000 | 0.3712 | 0.8391 | 0.8395 | | 0.392 | 21.69 | 7200 | 0.3669 | 0.8409 | 0.8410 | | 0.3875 | 22.29 | 7400 | 0.3689 | 0.8395 | 0.8396 | | 0.3884 | 22.89 | 7600 | 0.3674 | 0.8399 | 0.8400 | | 0.3894 | 23.49 | 7800 | 0.3684 | 0.8393 | 0.8395 | | 0.3905 | 24.1 | 8000 | 0.3692 | 0.8371 | 0.8374 | | 0.3915 | 24.7 | 8200 | 0.3718 | 0.8374 | 0.8378 | | 0.3847 | 25.3 | 8400 | 0.3688 | 0.8385 | 0.8387 | | 0.392 | 25.9 | 8600 | 0.3667 | 0.8388 | 0.8389 | | 0.3841 | 26.51 | 8800 | 0.3659 | 0.8409 | 0.8410 | | 0.3908 | 27.11 | 9000 | 0.3665 | 0.8401 | 0.8402 | | 0.395 | 27.71 | 9200 | 0.3668 | 0.8399 | 0.8400 | | 0.381 | 28.31 | 9400 | 0.3687 | 0.8379 | 0.8381 | | 0.3861 | 28.92 | 9600 | 0.3671 | 0.8401 | 0.8402 | | 0.389 | 29.52 | 9800 | 0.3668 | 0.8397 | 0.8398 | | 0.3852 | 30.12 | 10000 | 0.3671 | 0.8395 | 0.8396 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_65536_512_47M-L1_f

2024-05-03T15:20:43+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_notata-seqsight\_65536\_512\_47M-L1\_f ============================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3864 * F1 Score: 0.8244 * Accuracy: 0.8244 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

golf2248/0tx35ru

2024-05-03T15:20:46+00:00

TAGS #transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

ferrazzipietro/LS_Llama-2-7b-hf_adapters_en.layer1_NoQuant_16_32_0.01_2_5e-05

2024-05-03T15:21:11+00:00

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

GamblerOnTrain/SVVRT-056

2024-05-03T15:21:33+00:00

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_notata-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3801 - F1 Score: 0.8340 - Accuracy: 0.8340 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5157 | 0.6 | 200 | 0.4057 | 0.8200 | 0.8200 | | 0.4395 | 1.2 | 400 | 0.3923 | 0.8217 | 0.8217 | | 0.4266 | 1.81 | 600 | 0.3870 | 0.8294 | 0.8297 | | 0.4216 | 2.41 | 800 | 0.3815 | 0.8321 | 0.8323 | | 0.4095 | 3.01 | 1000 | 0.3764 | 0.8365 | 0.8366 | | 0.4021 | 3.61 | 1200 | 0.3719 | 0.8380 | 0.8381 | | 0.4034 | 4.22 | 1400 | 0.3716 | 0.8390 | 0.8391 | | 0.3982 | 4.82 | 1600 | 0.3706 | 0.8380 | 0.8381 | | 0.3892 | 5.42 | 1800 | 0.3697 | 0.8353 | 0.8353 | | 0.3977 | 6.02 | 2000 | 0.3695 | 0.8351 | 0.8353 | | 0.3907 | 6.63 | 2200 | 0.3662 | 0.8379 | 0.8379 | | 0.3894 | 7.23 | 2400 | 0.3675 | 0.8363 | 0.8364 | | 0.3885 | 7.83 | 2600 | 0.3639 | 0.8400 | 0.8400 | | 0.3812 | 8.43 | 2800 | 0.3776 | 0.8356 | 0.8363 | | 0.3867 | 9.04 | 3000 | 0.3635 | 0.8388 | 0.8389 | | 0.3821 | 9.64 | 3200 | 0.3619 | 0.8406 | 0.8406 | | 0.3834 | 10.24 | 3400 | 0.3633 | 0.8429 | 0.8428 | | 0.3795 | 10.84 | 3600 | 0.3624 | 0.8402 | 0.8402 | | 0.3827 | 11.45 | 3800 | 0.3629 | 0.8396 | 0.8396 | | 0.3808 | 12.05 | 4000 | 0.3613 | 0.8423 | 0.8423 | | 0.3767 | 12.65 | 4200 | 0.3626 | 0.8377 | 0.8378 | | 0.3818 | 13.25 | 4400 | 0.3647 | 0.8401 | 0.8402 | | 0.3808 | 13.86 | 4600 | 0.3640 | 0.8374 | 0.8376 | | 0.3783 | 14.46 | 4800 | 0.3617 | 0.8423 | 0.8423 | | 0.3744 | 15.06 | 5000 | 0.3615 | 0.8409 | 0.8410 | | 0.3724 | 15.66 | 5200 | 0.3626 | 0.8418 | 0.8419 | | 0.3746 | 16.27 | 5400 | 0.3630 | 0.8425 | 0.8425 | | 0.3748 | 16.87 | 5600 | 0.3674 | 0.8369 | 0.8372 | | 0.3706 | 17.47 | 5800 | 0.3653 | 0.8367 | 0.8370 | | 0.3794 | 18.07 | 6000 | 0.3651 | 0.8356 | 0.8359 | | 0.3705 | 18.67 | 6200 | 0.3613 | 0.8401 | 0.8402 | | 0.3787 | 19.28 | 6400 | 0.3603 | 0.8425 | 0.8425 | | 0.371 | 19.88 | 6600 | 0.3618 | 0.8389 | 0.8391 | | 0.3679 | 20.48 | 6800 | 0.3607 | 0.8416 | 0.8417 | | 0.3756 | 21.08 | 7000 | 0.3655 | 0.8363 | 0.8366 | | 0.3741 | 21.69 | 7200 | 0.3615 | 0.8427 | 0.8427 | | 0.368 | 22.29 | 7400 | 0.3620 | 0.8387 | 0.8389 | | 0.3684 | 22.89 | 7600 | 0.3616 | 0.8397 | 0.8398 | | 0.3686 | 23.49 | 7800 | 0.3618 | 0.8413 | 0.8413 | | 0.3721 | 24.1 | 8000 | 0.3634 | 0.8393 | 0.8395 | | 0.3712 | 24.7 | 8200 | 0.3637 | 0.8375 | 0.8378 | | 0.3644 | 25.3 | 8400 | 0.3633 | 0.8395 | 0.8396 | | 0.3718 | 25.9 | 8600 | 0.3604 | 0.8430 | 0.8430 | | 0.3657 | 26.51 | 8800 | 0.3609 | 0.8438 | 0.8438 | | 0.3711 | 27.11 | 9000 | 0.3599 | 0.8442 | 0.8442 | | 0.3754 | 27.71 | 9200 | 0.3610 | 0.8408 | 0.8410 | | 0.3628 | 28.31 | 9400 | 0.3620 | 0.8393 | 0.8395 | | 0.3667 | 28.92 | 9600 | 0.3610 | 0.8426 | 0.8427 | | 0.3696 | 29.52 | 9800 | 0.3606 | 0.8433 | 0.8434 | | 0.3645 | 30.12 | 10000 | 0.3609 | 0.8431 | 0.8432 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_65536_512_47M-L8_f

2024-05-03T15:21:48+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_notata-seqsight\_65536\_512\_47M-L8\_f ============================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3801 * F1 Score: 0.8340 * Accuracy: 0.8340 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_notata-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3796 - F1 Score: 0.8315 - Accuracy: 0.8315 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5008 | 0.6 | 200 | 0.4040 | 0.8165 | 0.8168 | | 0.4283 | 1.2 | 400 | 0.3796 | 0.8312 | 0.8312 | | 0.4079 | 1.81 | 600 | 0.3836 | 0.8283 | 0.8287 | | 0.4023 | 2.41 | 800 | 0.3711 | 0.8344 | 0.8346 | | 0.3962 | 3.01 | 1000 | 0.3707 | 0.8383 | 0.8385 | | 0.389 | 3.61 | 1200 | 0.3654 | 0.8412 | 0.8413 | | 0.3926 | 4.22 | 1400 | 0.3682 | 0.8408 | 0.8410 | | 0.3888 | 4.82 | 1600 | 0.3669 | 0.8378 | 0.8379 | | 0.3781 | 5.42 | 1800 | 0.3697 | 0.8383 | 0.8383 | | 0.387 | 6.02 | 2000 | 0.3681 | 0.8365 | 0.8368 | | 0.3786 | 6.63 | 2200 | 0.3636 | 0.8402 | 0.8402 | | 0.378 | 7.23 | 2400 | 0.3679 | 0.8360 | 0.8363 | | 0.3771 | 7.83 | 2600 | 0.3617 | 0.8419 | 0.8419 | | 0.3699 | 8.43 | 2800 | 0.3781 | 0.8320 | 0.8327 | | 0.3751 | 9.04 | 3000 | 0.3639 | 0.8400 | 0.8402 | | 0.3692 | 9.64 | 3200 | 0.3623 | 0.8390 | 0.8391 | | 0.3706 | 10.24 | 3400 | 0.3621 | 0.8423 | 0.8423 | | 0.3646 | 10.84 | 3600 | 0.3621 | 0.8422 | 0.8423 | | 0.3666 | 11.45 | 3800 | 0.3642 | 0.8418 | 0.8419 | | 0.3663 | 12.05 | 4000 | 0.3604 | 0.8413 | 0.8413 | | 0.3609 | 12.65 | 4200 | 0.3638 | 0.8386 | 0.8387 | | 0.3651 | 13.25 | 4400 | 0.3649 | 0.8387 | 0.8389 | | 0.3646 | 13.86 | 4600 | 0.3681 | 0.8380 | 0.8381 | | 0.3594 | 14.46 | 4800 | 0.3655 | 0.8399 | 0.8400 | | 0.3563 | 15.06 | 5000 | 0.3625 | 0.8390 | 0.8391 | | 0.3534 | 15.66 | 5200 | 0.3690 | 0.8376 | 0.8378 | | 0.3571 | 16.27 | 5400 | 0.3703 | 0.8398 | 0.8398 | | 0.3569 | 16.87 | 5600 | 0.3725 | 0.8343 | 0.8347 | | 0.3522 | 17.47 | 5800 | 0.3698 | 0.8363 | 0.8366 | | 0.3597 | 18.07 | 6000 | 0.3720 | 0.8343 | 0.8347 | | 0.3499 | 18.67 | 6200 | 0.3675 | 0.8395 | 0.8396 | | 0.3563 | 19.28 | 6400 | 0.3653 | 0.8409 | 0.8410 | | 0.3506 | 19.88 | 6600 | 0.3658 | 0.8384 | 0.8385 | | 0.3462 | 20.48 | 6800 | 0.3668 | 0.8410 | 0.8412 | | 0.3524 | 21.08 | 7000 | 0.3751 | 0.8349 | 0.8353 | | 0.3518 | 21.69 | 7200 | 0.3675 | 0.8417 | 0.8417 | | 0.3434 | 22.29 | 7400 | 0.3679 | 0.8385 | 0.8387 | | 0.345 | 22.89 | 7600 | 0.3703 | 0.8378 | 0.8379 | | 0.3451 | 23.49 | 7800 | 0.3697 | 0.8391 | 0.8393 | | 0.3481 | 24.1 | 8000 | 0.3733 | 0.8387 | 0.8389 | | 0.3467 | 24.7 | 8200 | 0.3731 | 0.8373 | 0.8376 | | 0.3411 | 25.3 | 8400 | 0.3717 | 0.8404 | 0.8406 | | 0.3473 | 25.9 | 8600 | 0.3677 | 0.8397 | 0.8398 | | 0.3419 | 26.51 | 8800 | 0.3690 | 0.8413 | 0.8413 | | 0.3469 | 27.11 | 9000 | 0.3687 | 0.8413 | 0.8413 | | 0.3502 | 27.71 | 9200 | 0.3694 | 0.8400 | 0.8402 | | 0.3371 | 28.31 | 9400 | 0.3713 | 0.8387 | 0.8389 | | 0.3417 | 28.92 | 9600 | 0.3704 | 0.8397 | 0.8398 | | 0.3454 | 29.52 | 9800 | 0.3692 | 0.8403 | 0.8404 | | 0.3395 | 30.12 | 10000 | 0.3698 | 0.8395 | 0.8396 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_65536_512_47M-L32_f

2024-05-03T15:21:49+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_notata-seqsight\_65536\_512\_47M-L32\_f ============================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3796 * F1 Score: 0.8315 * Accuracy: 0.8315 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

fmshahata/phi-moe-alt_2exp

2024-05-03T15:22:04+00:00

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_tata-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4610 - F1 Score: 0.8057 - Accuracy: 0.8059 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5888 | 5.13 | 200 | 0.5903 | 0.6887 | 0.6933 | | 0.5479 | 10.26 | 400 | 0.5702 | 0.6984 | 0.6998 | | 0.5342 | 15.38 | 600 | 0.5753 | 0.7011 | 0.7047 | | 0.5238 | 20.51 | 800 | 0.5627 | 0.7058 | 0.7080 | | 0.5135 | 25.64 | 1000 | 0.5604 | 0.7143 | 0.7145 | | 0.5061 | 30.77 | 1200 | 0.5629 | 0.7194 | 0.7210 | | 0.497 | 35.9 | 1400 | 0.5553 | 0.7237 | 0.7243 | | 0.4918 | 41.03 | 1600 | 0.5495 | 0.7208 | 0.7210 | | 0.485 | 46.15 | 1800 | 0.5529 | 0.7376 | 0.7390 | | 0.4789 | 51.28 | 2000 | 0.5491 | 0.7366 | 0.7374 | | 0.4682 | 56.41 | 2200 | 0.5477 | 0.7414 | 0.7423 | | 0.4641 | 61.54 | 2400 | 0.5323 | 0.7503 | 0.7504 | | 0.4583 | 66.67 | 2600 | 0.5328 | 0.7464 | 0.7471 | | 0.4528 | 71.79 | 2800 | 0.5201 | 0.7581 | 0.7586 | | 0.4407 | 76.92 | 3000 | 0.5141 | 0.7469 | 0.7471 | | 0.4287 | 82.05 | 3200 | 0.5026 | 0.7503 | 0.7504 | | 0.4239 | 87.18 | 3400 | 0.4992 | 0.7680 | 0.7684 | | 0.4189 | 92.31 | 3600 | 0.4950 | 0.7680 | 0.7684 | | 0.4108 | 97.44 | 3800 | 0.4868 | 0.7731 | 0.7732 | | 0.4103 | 102.56 | 4000 | 0.4842 | 0.7714 | 0.7716 | | 0.4035 | 107.69 | 4200 | 0.4797 | 0.7745 | 0.7749 | | 0.3967 | 112.82 | 4400 | 0.4762 | 0.7829 | 0.7830 | | 0.3925 | 117.95 | 4600 | 0.4789 | 0.7727 | 0.7732 | | 0.3959 | 123.08 | 4800 | 0.4746 | 0.7761 | 0.7765 | | 0.3854 | 128.21 | 5000 | 0.4735 | 0.7859 | 0.7863 | | 0.3856 | 133.33 | 5200 | 0.4708 | 0.7844 | 0.7847 | | 0.3852 | 138.46 | 5400 | 0.4624 | 0.7813 | 0.7814 | | 0.3762 | 143.59 | 5600 | 0.4680 | 0.7877 | 0.7879 | | 0.3772 | 148.72 | 5800 | 0.4702 | 0.7926 | 0.7928 | | 0.3748 | 153.85 | 6000 | 0.4687 | 0.7876 | 0.7879 | | 0.3721 | 158.97 | 6200 | 0.4668 | 0.7893 | 0.7896 | | 0.3696 | 164.1 | 6400 | 0.4762 | 0.7859 | 0.7863 | | 0.3716 | 169.23 | 6600 | 0.4582 | 0.7944 | 0.7945 | | 0.3694 | 174.36 | 6800 | 0.4635 | 0.7845 | 0.7847 | | 0.3631 | 179.49 | 7000 | 0.4616 | 0.7894 | 0.7896 | | 0.3615 | 184.62 | 7200 | 0.4657 | 0.7910 | 0.7912 | | 0.3627 | 189.74 | 7400 | 0.4635 | 0.7927 | 0.7928 | | 0.3586 | 194.87 | 7600 | 0.4637 | 0.7912 | 0.7912 | | 0.3615 | 200.0 | 7800 | 0.4559 | 0.7912 | 0.7912 | | 0.353 | 205.13 | 8000 | 0.4658 | 0.7877 | 0.7879 | | 0.3587 | 210.26 | 8200 | 0.4620 | 0.7861 | 0.7863 | | 0.3581 | 215.38 | 8400 | 0.4614 | 0.7843 | 0.7847 | | 0.3589 | 220.51 | 8600 | 0.4599 | 0.7877 | 0.7879 | | 0.3552 | 225.64 | 8800 | 0.4645 | 0.7958 | 0.7961 | | 0.3569 | 230.77 | 9000 | 0.4613 | 0.7926 | 0.7928 | | 0.3513 | 235.9 | 9200 | 0.4630 | 0.7926 | 0.7928 | | 0.3584 | 241.03 | 9400 | 0.4593 | 0.7910 | 0.7912 | | 0.3538 | 246.15 | 9600 | 0.4611 | 0.7926 | 0.7928 | | 0.3523 | 251.28 | 9800 | 0.4624 | 0.7926 | 0.7928 | | 0.3579 | 256.41 | 10000 | 0.4610 | 0.7926 | 0.7928 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_65536_512_47M-L1_f

2024-05-03T15:22:17+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_tata-seqsight\_65536\_512\_47M-L1\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4610 * F1 Score: 0.8057 * Accuracy: 0.8059 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

iimran/gemmaanalyser

2024-05-03T15:22:17+00:00

TAGS #transformers #safetensors #gemma #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-classification

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Prototipo_4_EMI This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.0406 - Accuracy: 0.5567 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 50 - eval_batch_size: 50 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:------:|:----:|:---------------:|:--------:| | 1.3118 | 0.3704 | 200 | 1.2660 | 0.4457 | | 1.0828 | 0.7407 | 400 | 1.0757 | 0.5203 | | 1.0145 | 1.1111 | 600 | 1.0380 | 0.534 | | 0.9955 | 1.4815 | 800 | 1.0184 | 0.5377 | | 0.9449 | 1.8519 | 1000 | 0.9944 | 0.5507 | | 0.9143 | 2.2222 | 1200 | 1.0077 | 0.5533 | | 0.8609 | 2.5926 | 1400 | 1.0104 | 0.5473 | | 0.882 | 2.9630 | 1600 | 1.0037 | 0.5507 | | 0.8049 | 3.3333 | 1800 | 1.0202 | 0.5593 | | 0.8045 | 3.7037 | 2000 | 1.0234 | 0.5503 | | 0.78 | 4.0741 | 2200 | 1.0280 | 0.5593 | | 0.7651 | 4.4444 | 2400 | 1.0411 | 0.5583 | | 0.7301 | 4.8148 | 2600 | 1.0406 | 0.5567 | ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "dccuchile/distilbert-base-spanish-uncased", "model-index": [{"name": "Prototipo_4_EMI", "results": []}]}

Armandodelca/Prototipo_4_EMI

2024-05-03T15:22:24+00:00

TAGS #transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-dccuchile/distilbert-base-spanish-uncased #autotrain_compatible #endpoints_compatible #region-us

Prototipo\_4\_EMI ================= This model is a fine-tuned version of dccuchile/distilbert-base-spanish-uncased on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 1.0406 * Accuracy: 0.5567 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 50 * eval\_batch\_size: 50 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_steps: 500 * num\_epochs: 5 * mixed\_precision\_training: Native AMP ### Training results ### Framework versions * Transformers 4.40.1 * Pytorch 2.2.1+cu121 * Datasets 2.19.0 * Tokenizers 0.19.1

text-to-image

diffusers

<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # SDXL LoRA DreamBooth - nghiatran00932/corgy_dog_LoRA <Gallery /> ## Model description These are nghiatran00932/corgy_dog_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use a photo of TOK dog to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](nghiatran00932/corgy_dog_LoRA/tree/main) them in the Files & versions tab. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]

{"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "text-to-image", "diffusers-training", "diffusers", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "a photo of TOK dog", "widget": []}

nghiatran00932/corgy_dog_LoRA

2024-05-03T15:22:41+00:00

TAGS #diffusers #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us

# SDXL LoRA DreamBooth - nghiatran00932/corgy_dog_LoRA <Gallery /> ## Model description These are nghiatran00932/corgy_dog_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using DreamBooth. LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use a photo of TOK dog to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. Download them in the Files & versions tab. ## Intended uses & limitations #### How to use #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]

text-generation

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.0` ```yaml base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 model_type: LlamaForCausalLM tokenizer_type: AutoTokenizer load_in_8bit: false load_in_4bit: false strict: false datasets: - path: /data/data/final_set_cleaned/train/ type: sharegpt conversation: chatml - path: /data/data/map_coig_cqia.jsonl type: sharegpt conversation: chatml - path: /data/data/ruozhiba.jsonl type: sharegpt conversation: chatml dataset_prepared_path: last_run_prepared val_set_size: 0 output_dir: ./out sequence_len: 4096 sample_packing: true pad_to_sequence_len: true wandb_project: FFT wandb_entity: wandb_watch: wandb_name: llama3-fft wandb_log_model: gradient_accumulation_steps: 8 micro_batch_size: 4 num_epochs: 2 optimizer: paged_adamw_8bit lr_scheduler: cosine learning_rate: 2e-5 train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: true gradient_checkpointing_kwargs: use_reentrant: false early_stopping_patience: resume_from_checkpoint: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 100 evals_per_epoch: 0 eval_table_size: saves_per_epoch: 4 save_total_limit: 8 debug: deepspeed: deepspeed/zero2.json weight_decay: 0.0 fsdp: fsdp_config: default_system_message: "You are a helpful assistant." special_tokens: eos_token: "<|im_end|>" pad_token: "<|end_of_text|>" tokens: - "<|im_start|>" - "<|im_end|>" ``` </details><br> # llama-1.1B-fft This model is a full parameter fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the SFT dataset for two epoches. It has a substantial improvement over several benchmark: | Groups |Version|Filter|n-shot|Metric|TinyLlama-1.1B-Chat-v1.0 |Ours |------------------|-------|------|-----:|------|-----:|-----: |mmlu |N/A |none | 0|acc |0.2463|0.3547 | - humanities |N/A |none | 0|acc |0.2493|0.3375 | - other |N/A |none | 0|acc |0.2588|0.3939 | - social_sciences|N/A |none | 0|acc |0.2304|0.3939 | - stem |N/A |none | 0|acc |0.2448|0.3035 |gsm8k | 3|strict-match | 5|exact_match|0.0243|0.1615| strong english chat ability, while still weak on Chinese conversation (may suffer from repeatition). ``` {"instruction": "What are the names of some famous actors that started their careers on Broadway?", "output": "Some famous actors who started their careers on Broadway include:\n\n1. Richard Rodgers\n2. George Abbott\n3. Jerome Robbins\n4. Lin-Manuel Miranda\n5. Stephen Sondheim\n6. Harold Prince\n7. Alfred Uhry\n8. Stephen Schwartz\n9. Joe Mantello\n10. Mike Nichols\n11. Robert Duvall\n12. Susan Sarandon\n13. Martin Katz\n14. Gwyneth Paltrow\n15. Audra McDonald."} {"instruction": "How do I wrap a present neatly?", "output": "There are several ways to wrap a present neatly, depending on the size and type of the present. Here are a few options:\n\n1. Wrap the present in a piece of wrapping paper. This will help to keep the wrapping clean and neat.\n2. Use a piece of tissue paper or a small piece of gift wrap to wrap the present. This will help to keep the wrapping clean and neat.\n3. Use a piece of string or ribbon to tie the present. This will help to keep the wrapping clean and neat.\n4. Use a piece of bubble wrap or packing paper to wrap the present. This will help to keep the wrapping clean and neat.\n5. Use a small piece of gift wrap or a piece of tissue paper to wrap the present. This will help to keep the wrapping clean and neat.\n\nIt's important to keep in mind that the wrapping should be tight and secure, so that the gift is not damaged during transportation."} {"instruction": "我正在设计一款专为老年人设计的人工智能手机，你能帮我写个宣传文案吗？", "output": "设计了一款专为老年人设计的人工智能手机，现在正在积极推广！\n它的功能齐全，智能操控能力极强，无论是拍照、观看视频，还是拍摄照片，都无所疑。\n此前，我们在欧洲设计的一款人工智能手机，很好的满足了老年人的需求，使用起来非常方便。\n此前，我们在美国设计的一款人工智能手机，也很好的满足了老年人的需求，使用起来非常方便。\n现在，我们在世界各地设计的一款人工智能手机，都很好的满足了老年人的需求，使用起来非常方便。\n谁都不愿意老退化，老年人不受孤僻和孤立的痛苦，他们只想要生活在一个人情味的世界里。\n老年人不受孤僻和孤立的痛苦，他们只想要生活在一个人情味的世界里。\n老年人不受孤僻和孤立的痛苦，他们只想要生活在一个人情味的世界里。\n我们欢迎您使用我们发布的人工智能手机，不受孤僻和孤立的痛苦，您的生活将更加美好！"} ``` ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 2 - gradient_accumulation_steps: 8 - total_train_batch_size: 64 - total_eval_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - num_epochs: 2 ### Training results ### Framework versions - Transformers 4.40.1 - Pytorch 2.0.1+cu118 - Datasets 2.15.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "model-index": [{"name": "data/llama-1B-20240502-0131", "results": []}]}

lu-vae/llama-1.1B-fft

2024-05-03T15:23:16+00:00

TAGS #transformers #pytorch #llama #text-generation #generated_from_trainer #conversational #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

<img src="URL alt="Built with Axolotl" width="200" height="32"/> See axolotl config axolotl version: '0.4.0' llama-1.1B-fft ============== This model is a full parameter fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the SFT dataset for two epoches. It has a substantial improvement over several benchmark: strong english chat ability, while still weak on Chinese conversation (may suffer from repeatition). Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 4 * eval\_batch\_size: 4 * seed: 42 * distributed\_type: multi-GPU * num\_devices: 2 * gradient\_accumulation\_steps: 8 * total\_train\_batch\_size: 64 * total\_eval\_batch\_size: 8 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: cosine * lr\_scheduler\_warmup\_steps: 100 * num\_epochs: 2 ### Training results ### Framework versions * Transformers 4.40.1 * Pytorch 2.0.1+cu118 * Datasets 2.15.0 * Tokenizers 0.19.1

text-classification

transformers

# Model Trained Using AutoTrain - Problem type: Text Classification ## Validation Metrics loss: 0.12401879578828812 f1: 0.9685289508238384 precision: 0.9893561786085151 recall: 0.9485605243507841 auc: 0.9904075461390904 accuracy: 0.9672355249812585

{"tags": ["autotrain", "text-classification"], "datasets": ["autotrain-V2-Proedge-New-2/autotrain-data"], "widget": [{"text": "I love AutoTrain"}]}

purpleor/autotrain-V2-Proedge-New-2

2024-05-03T15:24:56+00:00

TAGS #transformers #tensorboard #safetensors #deberta-v2 #text-classification #autotrain #dataset-autotrain-V2-Proedge-New-2/autotrain-data #autotrain_compatible #endpoints_compatible #region-us

# Model Trained Using AutoTrain - Problem type: Text Classification ## Validation Metrics loss: 0.12401879578828812 f1: 0.9685289508238384 precision: 0.9893561786085151 recall: 0.9485605243507841 auc: 0.9904075461390904 accuracy: 0.9672355249812585

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_tata-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.5221 - F1 Score: 0.8091 - Accuracy: 0.8091 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.575 | 5.13 | 200 | 0.5788 | 0.6986 | 0.7031 | | 0.5243 | 10.26 | 400 | 0.5731 | 0.7076 | 0.7129 | | 0.4993 | 15.38 | 600 | 0.5706 | 0.7196 | 0.7243 | | 0.4751 | 20.51 | 800 | 0.5391 | 0.7455 | 0.7455 | | 0.4527 | 25.64 | 1000 | 0.5309 | 0.7596 | 0.7602 | | 0.4255 | 30.77 | 1200 | 0.4852 | 0.7585 | 0.7586 | | 0.3924 | 35.9 | 1400 | 0.4728 | 0.7942 | 0.7945 | | 0.3738 | 41.03 | 1600 | 0.4622 | 0.7810 | 0.7814 | | 0.3603 | 46.15 | 1800 | 0.4587 | 0.7973 | 0.7977 | | 0.3445 | 51.28 | 2000 | 0.4725 | 0.8021 | 0.8026 | | 0.3376 | 56.41 | 2200 | 0.4463 | 0.7993 | 0.7993 | | 0.3277 | 61.54 | 2400 | 0.4496 | 0.8107 | 0.8108 | | 0.319 | 66.67 | 2600 | 0.4687 | 0.7964 | 0.7977 | | 0.3079 | 71.79 | 2800 | 0.4413 | 0.8238 | 0.8238 | | 0.299 | 76.92 | 3000 | 0.4664 | 0.8000 | 0.8010 | | 0.2938 | 82.05 | 3200 | 0.4357 | 0.8123 | 0.8124 | | 0.2805 | 87.18 | 3400 | 0.4604 | 0.8016 | 0.8026 | | 0.2779 | 92.31 | 3600 | 0.4253 | 0.8220 | 0.8222 | | 0.2708 | 97.44 | 3800 | 0.4226 | 0.8156 | 0.8157 | | 0.2675 | 102.56 | 4000 | 0.4257 | 0.8124 | 0.8124 | | 0.2622 | 107.69 | 4200 | 0.4286 | 0.8155 | 0.8157 | | 0.2593 | 112.82 | 4400 | 0.4290 | 0.8205 | 0.8206 | | 0.2477 | 117.95 | 4600 | 0.4316 | 0.8205 | 0.8206 | | 0.25 | 123.08 | 4800 | 0.4429 | 0.8189 | 0.8189 | | 0.2405 | 128.21 | 5000 | 0.4372 | 0.8173 | 0.8173 | | 0.2431 | 133.33 | 5200 | 0.4280 | 0.8254 | 0.8254 | | 0.237 | 138.46 | 5400 | 0.4314 | 0.8271 | 0.8271 | | 0.2323 | 143.59 | 5600 | 0.4319 | 0.8287 | 0.8287 | | 0.2286 | 148.72 | 5800 | 0.4470 | 0.8270 | 0.8271 | | 0.2294 | 153.85 | 6000 | 0.4371 | 0.8270 | 0.8271 | | 0.222 | 158.97 | 6200 | 0.4509 | 0.8254 | 0.8254 | | 0.2161 | 164.1 | 6400 | 0.4642 | 0.8268 | 0.8271 | | 0.2197 | 169.23 | 6600 | 0.4706 | 0.8300 | 0.8303 | | 0.2167 | 174.36 | 6800 | 0.4608 | 0.8286 | 0.8287 | | 0.2106 | 179.49 | 7000 | 0.4635 | 0.8201 | 0.8206 | | 0.2075 | 184.62 | 7200 | 0.4630 | 0.8252 | 0.8254 | | 0.2081 | 189.74 | 7400 | 0.4657 | 0.8285 | 0.8287 | | 0.2 | 194.87 | 7600 | 0.4670 | 0.8270 | 0.8271 | | 0.2078 | 200.0 | 7800 | 0.4502 | 0.8319 | 0.8320 | | 0.2027 | 205.13 | 8000 | 0.4664 | 0.8269 | 0.8271 | | 0.205 | 210.26 | 8200 | 0.4618 | 0.8302 | 0.8303 | | 0.2014 | 215.38 | 8400 | 0.4687 | 0.8268 | 0.8271 | | 0.2051 | 220.51 | 8600 | 0.4691 | 0.8285 | 0.8287 | | 0.199 | 225.64 | 8800 | 0.4762 | 0.8250 | 0.8254 | | 0.1972 | 230.77 | 9000 | 0.4646 | 0.8286 | 0.8287 | | 0.1966 | 235.9 | 9200 | 0.4698 | 0.8350 | 0.8352 | | 0.1962 | 241.03 | 9400 | 0.4740 | 0.8318 | 0.8320 | | 0.1964 | 246.15 | 9600 | 0.4773 | 0.8318 | 0.8320 | | 0.1941 | 251.28 | 9800 | 0.4747 | 0.8302 | 0.8303 | | 0.1977 | 256.41 | 10000 | 0.4716 | 0.8335 | 0.8336 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_65536_512_47M-L8_f

2024-05-03T15:24:57+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_tata-seqsight\_65536\_512\_47M-L8\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.5221 * F1 Score: 0.8091 * Accuracy: 0.8091 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"license": "mit"}

RobertLeichtveis/ModelOne

2024-05-03T15:25:15+00:00

TAGS #arxiv-1910.09700 #license-mit #region-us

# Model Card for Model ID This modelcard aims to be a base template for new models. It has been generated using this raw template. ## Model Details ### Model Description - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_tata-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.6611 - F1 Score: 0.8090 - Accuracy: 0.8091 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5627 | 5.13 | 200 | 0.5615 | 0.7109 | 0.7129 | | 0.5027 | 10.26 | 400 | 0.5782 | 0.7275 | 0.7325 | | 0.4619 | 15.38 | 600 | 0.5295 | 0.7481 | 0.7488 | | 0.4103 | 20.51 | 800 | 0.4771 | 0.7830 | 0.7830 | | 0.3681 | 25.64 | 1000 | 0.4999 | 0.7934 | 0.7945 | | 0.336 | 30.77 | 1200 | 0.4624 | 0.7912 | 0.7912 | | 0.3058 | 35.9 | 1400 | 0.4571 | 0.8042 | 0.8042 | | 0.2809 | 41.03 | 1600 | 0.4659 | 0.8107 | 0.8108 | | 0.2649 | 46.15 | 1800 | 0.4670 | 0.8188 | 0.8189 | | 0.2413 | 51.28 | 2000 | 0.5184 | 0.8137 | 0.8140 | | 0.2273 | 56.41 | 2200 | 0.5089 | 0.8173 | 0.8173 | | 0.2117 | 61.54 | 2400 | 0.4994 | 0.8254 | 0.8254 | | 0.1958 | 66.67 | 2600 | 0.5513 | 0.8187 | 0.8189 | | 0.1832 | 71.79 | 2800 | 0.5467 | 0.8287 | 0.8287 | | 0.1765 | 76.92 | 3000 | 0.5956 | 0.8035 | 0.8042 | | 0.1664 | 82.05 | 3200 | 0.6005 | 0.8221 | 0.8222 | | 0.1539 | 87.18 | 3400 | 0.5867 | 0.8106 | 0.8108 | | 0.147 | 92.31 | 3600 | 0.5988 | 0.8254 | 0.8254 | | 0.139 | 97.44 | 3800 | 0.6216 | 0.8222 | 0.8222 | | 0.1309 | 102.56 | 4000 | 0.6519 | 0.8171 | 0.8173 | | 0.1328 | 107.69 | 4200 | 0.6261 | 0.8320 | 0.8320 | | 0.1196 | 112.82 | 4400 | 0.6704 | 0.8153 | 0.8157 | | 0.113 | 117.95 | 4600 | 0.6755 | 0.8254 | 0.8254 | | 0.1153 | 123.08 | 4800 | 0.6763 | 0.8220 | 0.8222 | | 0.1077 | 128.21 | 5000 | 0.6611 | 0.8222 | 0.8222 | | 0.104 | 133.33 | 5200 | 0.6954 | 0.8205 | 0.8206 | | 0.0995 | 138.46 | 5400 | 0.7337 | 0.8157 | 0.8157 | | 0.0964 | 143.59 | 5600 | 0.7265 | 0.8140 | 0.8140 | | 0.0908 | 148.72 | 5800 | 0.7575 | 0.8140 | 0.8140 | | 0.092 | 153.85 | 6000 | 0.7395 | 0.8108 | 0.8108 | | 0.0893 | 158.97 | 6200 | 0.7470 | 0.8140 | 0.8140 | | 0.0807 | 164.1 | 6400 | 0.7726 | 0.8107 | 0.8108 | | 0.0834 | 169.23 | 6600 | 0.8118 | 0.8026 | 0.8026 | | 0.0804 | 174.36 | 6800 | 0.7895 | 0.8107 | 0.8108 | | 0.0756 | 179.49 | 7000 | 0.7893 | 0.8075 | 0.8075 | | 0.0793 | 184.62 | 7200 | 0.8090 | 0.8058 | 0.8059 | | 0.0732 | 189.74 | 7400 | 0.8277 | 0.8122 | 0.8124 | | 0.0735 | 194.87 | 7600 | 0.8021 | 0.8140 | 0.8140 | | 0.0762 | 200.0 | 7800 | 0.7905 | 0.8124 | 0.8124 | | 0.0709 | 205.13 | 8000 | 0.8231 | 0.8091 | 0.8091 | | 0.0683 | 210.26 | 8200 | 0.8386 | 0.8059 | 0.8059 | | 0.0692 | 215.38 | 8400 | 0.8389 | 0.8075 | 0.8075 | | 0.0668 | 220.51 | 8600 | 0.8597 | 0.8156 | 0.8157 | | 0.0669 | 225.64 | 8800 | 0.8714 | 0.8120 | 0.8124 | | 0.0634 | 230.77 | 9000 | 0.8592 | 0.8108 | 0.8108 | | 0.0633 | 235.9 | 9200 | 0.8775 | 0.8155 | 0.8157 | | 0.0652 | 241.03 | 9400 | 0.8725 | 0.8139 | 0.8140 | | 0.0684 | 246.15 | 9600 | 0.8589 | 0.8058 | 0.8059 | | 0.0614 | 251.28 | 9800 | 0.8666 | 0.8091 | 0.8091 | | 0.0656 | 256.41 | 10000 | 0.8666 | 0.8058 | 0.8059 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_65536_512_47M-L32_f

2024-05-03T15:25:43+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_core\_tata-seqsight\_65536\_512\_47M-L32\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.6611 * F1 Score: 0.8090 * Accuracy: 0.8091 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-classification

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # robust_llm_pythia-160m_niki-041a_imdb_random-token-1280_10-rounds_seed-2 This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 2 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-160m", "model-index": [{"name": "robust_llm_pythia-160m_niki-041a_imdb_random-token-1280_10-rounds_seed-2", "results": []}]}

AlignmentResearch/robust_llm_pythia-160m_niki-041a_imdb_random-token-1280_10-rounds_seed-2

2024-05-03T15:26:10+00:00

TAGS #transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-160m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# robust_llm_pythia-160m_niki-041a_imdb_random-token-1280_10-rounds_seed-2 This model is a fine-tuned version of EleutherAI/pythia-160m on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 2 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_all-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.2250 - F1 Score: 0.9089 - Accuracy: 0.9090 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.4111 | 0.54 | 200 | 0.2928 | 0.8952 | 0.8953 | | 0.2969 | 1.08 | 400 | 0.2567 | 0.9000 | 0.9 | | 0.2812 | 1.62 | 600 | 0.2457 | 0.9020 | 0.9020 | | 0.2633 | 2.16 | 800 | 0.2472 | 0.9027 | 0.9029 | | 0.2628 | 2.7 | 1000 | 0.2334 | 0.9027 | 0.9027 | | 0.2523 | 3.24 | 1200 | 0.2369 | 0.9062 | 0.9062 | | 0.252 | 3.78 | 1400 | 0.2283 | 0.9077 | 0.9078 | | 0.2508 | 4.32 | 1600 | 0.2258 | 0.9082 | 0.9083 | | 0.2407 | 4.86 | 1800 | 0.2250 | 0.9076 | 0.9076 | | 0.2401 | 5.41 | 2000 | 0.2231 | 0.9091 | 0.9091 | | 0.24 | 5.95 | 2200 | 0.2264 | 0.9099 | 0.9100 | | 0.2377 | 6.49 | 2400 | 0.2226 | 0.9092 | 0.9093 | | 0.2363 | 7.03 | 2600 | 0.2182 | 0.9110 | 0.9110 | | 0.2315 | 7.57 | 2800 | 0.2187 | 0.9103 | 0.9103 | | 0.2335 | 8.11 | 3000 | 0.2156 | 0.9123 | 0.9123 | | 0.23 | 8.65 | 3200 | 0.2145 | 0.9118 | 0.9118 | | 0.2236 | 9.19 | 3400 | 0.2138 | 0.9130 | 0.9130 | | 0.2257 | 9.73 | 3600 | 0.2125 | 0.9154 | 0.9154 | | 0.2305 | 10.27 | 3800 | 0.2112 | 0.9135 | 0.9135 | | 0.2246 | 10.81 | 4000 | 0.2122 | 0.9132 | 0.9132 | | 0.2265 | 11.35 | 4200 | 0.2142 | 0.9143 | 0.9144 | | 0.2203 | 11.89 | 4400 | 0.2108 | 0.9152 | 0.9152 | | 0.2191 | 12.43 | 4600 | 0.2125 | 0.9145 | 0.9145 | | 0.2226 | 12.97 | 4800 | 0.2082 | 0.9164 | 0.9164 | | 0.2166 | 13.51 | 5000 | 0.2092 | 0.9159 | 0.9159 | | 0.2224 | 14.05 | 5200 | 0.2082 | 0.9164 | 0.9164 | | 0.2167 | 14.59 | 5400 | 0.2103 | 0.9165 | 0.9166 | | 0.2151 | 15.14 | 5600 | 0.2080 | 0.9175 | 0.9176 | | 0.2164 | 15.68 | 5800 | 0.2070 | 0.9162 | 0.9162 | | 0.2167 | 16.22 | 6000 | 0.2077 | 0.9182 | 0.9182 | | 0.215 | 16.76 | 6200 | 0.2084 | 0.9189 | 0.9189 | | 0.2134 | 17.3 | 6400 | 0.2065 | 0.9169 | 0.9169 | | 0.2165 | 17.84 | 6600 | 0.2068 | 0.9176 | 0.9176 | | 0.2116 | 18.38 | 6800 | 0.2065 | 0.9177 | 0.9177 | | 0.2166 | 18.92 | 7000 | 0.2063 | 0.9181 | 0.9181 | | 0.2135 | 19.46 | 7200 | 0.2060 | 0.9184 | 0.9184 | | 0.2134 | 20.0 | 7400 | 0.2058 | 0.9189 | 0.9189 | | 0.2168 | 20.54 | 7600 | 0.2039 | 0.9198 | 0.9198 | | 0.211 | 21.08 | 7800 | 0.2045 | 0.9199 | 0.9199 | | 0.213 | 21.62 | 8000 | 0.2049 | 0.9182 | 0.9182 | | 0.2099 | 22.16 | 8200 | 0.2045 | 0.9192 | 0.9193 | | 0.2051 | 22.7 | 8400 | 0.2046 | 0.9201 | 0.9201 | | 0.215 | 23.24 | 8600 | 0.2036 | 0.9194 | 0.9194 | | 0.2101 | 23.78 | 8800 | 0.2043 | 0.9184 | 0.9184 | | 0.2117 | 24.32 | 9000 | 0.2035 | 0.9196 | 0.9196 | | 0.2069 | 24.86 | 9200 | 0.2037 | 0.9199 | 0.9199 | | 0.21 | 25.41 | 9400 | 0.2034 | 0.9191 | 0.9191 | | 0.2102 | 25.95 | 9600 | 0.2035 | 0.9187 | 0.9187 | | 0.2105 | 26.49 | 9800 | 0.2039 | 0.9194 | 0.9194 | | 0.2095 | 27.03 | 10000 | 0.2038 | 0.9198 | 0.9198 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_65536_512_47M-L1_f

2024-05-03T15:26:46+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_300\_all-seqsight\_65536\_512\_47M-L1\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.2250 * F1 Score: 0.9089 * Accuracy: 0.9090 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

question-answering

transformers

## Introduction This TinyLlama1.1B model is finetuned from the base model. The goal is to finetune the model to make it suitable for RAG applications. The base models often perform poor on user query generating out of context response. There are also the problem of hallucination in LLMs. It refers to the case when LLMs generates incorrect answers rather than skipping the user question by appropriate response. To address this issue I have finetuned the base model by a hybride dataset which contains both meaningful question, context and answers and it also contains the question to which LLMs hallucinate and its proper response. This way of finetuning may reduce the hallucination rate of the model. ## How to use **Install dependencies** ```bash pip install -q accelerate==0.21.0 peft==0.4.0 bitsandbytes==0.40.2 transformers==4.31.0 trl==0.4.7 ``` You can use the following code for model inference. ```Python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline import pprint torch.set_default_device("cuda") #Create model model = AutoModelForCausalLM.from_pretrained("MuntasirAhmed/TinyLlama-1.1B-rag-finetuned-v1.0", torch_dtype=torch.float16, device_map="auto", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("MuntasirAhmed/TinyLlama-1.1B-rag-finetuned-v1.0", trust_remote_code=True) pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200) #Set inputs prompt = "What is a large language model?" formated_prompt = f'''<|system|> You are a friendly chatbot who responses to the user's question by looking into context.</s> <|user|> {prompt}</s> ''' #Generate the answer result = pipe(formated_prompt) pprint.pp(result[0]['generated_text']) ```

{"language": ["en"], "license": "mit", "library_name": "transformers", "pipeline_tag": "question-answering"}

muntasir2179/TinyLlama-1.1B-rag-finetuned-v1.0

2024-05-03T15:27:39+00:00

TAGS #transformers #pytorch #llama #text-generation #question-answering #en #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

## Introduction This TinyLlama1.1B model is finetuned from the base model. The goal is to finetune the model to make it suitable for RAG applications. The base models often perform poor on user query generating out of context response. There are also the problem of hallucination in LLMs. It refers to the case when LLMs generates incorrect answers rather than skipping the user question by appropriate response. To address this issue I have finetuned the base model by a hybride dataset which contains both meaningful question, context and answers and it also contains the question to which LLMs hallucinate and its proper response. This way of finetuning may reduce the hallucination rate of the model. ## How to use Install dependencies You can use the following code for model inference.

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_all-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.2089 - F1 Score: 0.9162 - Accuracy: 0.9162 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.3683 | 0.54 | 200 | 0.2543 | 0.8991 | 0.8992 | | 0.2675 | 1.08 | 400 | 0.2341 | 0.9076 | 0.9076 | | 0.2532 | 1.62 | 600 | 0.2194 | 0.9111 | 0.9111 | | 0.2329 | 2.16 | 800 | 0.2209 | 0.9124 | 0.9125 | | 0.2309 | 2.7 | 1000 | 0.2109 | 0.9149 | 0.9149 | | 0.2229 | 3.24 | 1200 | 0.2200 | 0.9126 | 0.9127 | | 0.2224 | 3.78 | 1400 | 0.2089 | 0.9158 | 0.9159 | | 0.2203 | 4.32 | 1600 | 0.2002 | 0.9231 | 0.9231 | | 0.2119 | 4.86 | 1800 | 0.2054 | 0.9182 | 0.9182 | | 0.211 | 5.41 | 2000 | 0.2027 | 0.9218 | 0.9218 | | 0.211 | 5.95 | 2200 | 0.2034 | 0.9206 | 0.9206 | | 0.2092 | 6.49 | 2400 | 0.1972 | 0.9216 | 0.9216 | | 0.2071 | 7.03 | 2600 | 0.1959 | 0.9214 | 0.9215 | | 0.2022 | 7.57 | 2800 | 0.1947 | 0.9223 | 0.9223 | | 0.2048 | 8.11 | 3000 | 0.1942 | 0.9242 | 0.9242 | | 0.1998 | 8.65 | 3200 | 0.1950 | 0.9213 | 0.9213 | | 0.1941 | 9.19 | 3400 | 0.1959 | 0.9203 | 0.9203 | | 0.1969 | 9.73 | 3600 | 0.1922 | 0.9220 | 0.9220 | | 0.2028 | 10.27 | 3800 | 0.1935 | 0.9236 | 0.9236 | | 0.1969 | 10.81 | 4000 | 0.1925 | 0.9228 | 0.9228 | | 0.2002 | 11.35 | 4200 | 0.1942 | 0.9229 | 0.9230 | | 0.1927 | 11.89 | 4400 | 0.1929 | 0.9252 | 0.9252 | | 0.1939 | 12.43 | 4600 | 0.1920 | 0.9233 | 0.9233 | | 0.1935 | 12.97 | 4800 | 0.1936 | 0.9225 | 0.9225 | | 0.189 | 13.51 | 5000 | 0.1933 | 0.9213 | 0.9213 | | 0.1948 | 14.05 | 5200 | 0.1948 | 0.9176 | 0.9176 | | 0.1884 | 14.59 | 5400 | 0.1938 | 0.9230 | 0.9230 | | 0.1886 | 15.14 | 5600 | 0.1913 | 0.9238 | 0.9238 | | 0.1898 | 15.68 | 5800 | 0.1917 | 0.9214 | 0.9215 | | 0.1889 | 16.22 | 6000 | 0.1915 | 0.9240 | 0.9240 | | 0.1879 | 16.76 | 6200 | 0.1908 | 0.9238 | 0.9238 | | 0.1869 | 17.3 | 6400 | 0.1907 | 0.9216 | 0.9216 | | 0.1896 | 17.84 | 6600 | 0.1888 | 0.9247 | 0.9247 | | 0.1829 | 18.38 | 6800 | 0.1911 | 0.9225 | 0.9225 | | 0.1902 | 18.92 | 7000 | 0.1890 | 0.9230 | 0.9230 | | 0.188 | 19.46 | 7200 | 0.1880 | 0.9252 | 0.9252 | | 0.186 | 20.0 | 7400 | 0.1884 | 0.9236 | 0.9236 | | 0.1894 | 20.54 | 7600 | 0.1870 | 0.9250 | 0.925 | | 0.1813 | 21.08 | 7800 | 0.1869 | 0.9253 | 0.9253 | | 0.1851 | 21.62 | 8000 | 0.1872 | 0.9248 | 0.9248 | | 0.1808 | 22.16 | 8200 | 0.1879 | 0.9245 | 0.9245 | | 0.1788 | 22.7 | 8400 | 0.1891 | 0.9248 | 0.9248 | | 0.1865 | 23.24 | 8600 | 0.1876 | 0.9247 | 0.9247 | | 0.1823 | 23.78 | 8800 | 0.1890 | 0.9236 | 0.9236 | | 0.1829 | 24.32 | 9000 | 0.1872 | 0.9252 | 0.9252 | | 0.1784 | 24.86 | 9200 | 0.1881 | 0.9252 | 0.9252 | | 0.1828 | 25.41 | 9400 | 0.1874 | 0.9255 | 0.9255 | | 0.181 | 25.95 | 9600 | 0.1875 | 0.9252 | 0.9252 | | 0.1836 | 26.49 | 9800 | 0.1878 | 0.9248 | 0.9248 | | 0.18 | 27.03 | 10000 | 0.1878 | 0.9247 | 0.9247 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_65536_512_47M-L8_f

2024-05-03T15:27:51+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_300\_all-seqsight\_65536\_512\_47M-L8\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.2089 * F1 Score: 0.9162 * Accuracy: 0.9162 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K14ac-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5178 - F1 Score: 0.7429 - Accuracy: 0.7419 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6123 | 0.97 | 200 | 0.5736 | 0.7023 | 0.7005 | | 0.5725 | 1.93 | 400 | 0.5567 | 0.7238 | 0.7219 | | 0.5656 | 2.9 | 600 | 0.5624 | 0.7206 | 0.7189 | | 0.5582 | 3.86 | 800 | 0.5356 | 0.7378 | 0.7389 | | 0.552 | 4.83 | 1000 | 0.5610 | 0.7240 | 0.7225 | | 0.5501 | 5.8 | 1200 | 0.5582 | 0.7265 | 0.7250 | | 0.5477 | 6.76 | 1400 | 0.5575 | 0.7273 | 0.7259 | | 0.5457 | 7.73 | 1600 | 0.5365 | 0.7431 | 0.7413 | | 0.5394 | 8.7 | 1800 | 0.5356 | 0.7443 | 0.7425 | | 0.5406 | 9.66 | 2000 | 0.5361 | 0.7416 | 0.7398 | | 0.541 | 10.63 | 2200 | 0.5583 | 0.7257 | 0.7247 | | 0.5346 | 11.59 | 2400 | 0.5328 | 0.7464 | 0.7446 | | 0.5368 | 12.56 | 2600 | 0.5434 | 0.7405 | 0.7389 | | 0.5332 | 13.53 | 2800 | 0.5413 | 0.7366 | 0.7349 | | 0.531 | 14.49 | 3000 | 0.5577 | 0.7252 | 0.7244 | | 0.5283 | 15.46 | 3200 | 0.5225 | 0.7498 | 0.7483 | | 0.532 | 16.43 | 3400 | 0.5514 | 0.7281 | 0.7271 | | 0.5297 | 17.39 | 3600 | 0.5304 | 0.7455 | 0.7437 | | 0.5269 | 18.36 | 3800 | 0.5187 | 0.7539 | 0.7525 | | 0.5251 | 19.32 | 4000 | 0.5344 | 0.7414 | 0.7398 | | 0.5239 | 20.29 | 4200 | 0.5305 | 0.7449 | 0.7431 | | 0.5243 | 21.26 | 4400 | 0.5430 | 0.7360 | 0.7346 | | 0.5254 | 22.22 | 4600 | 0.5456 | 0.7349 | 0.7337 | | 0.5248 | 23.19 | 4800 | 0.5268 | 0.7454 | 0.7437 | | 0.5227 | 24.15 | 5000 | 0.5296 | 0.7442 | 0.7425 | | 0.5204 | 25.12 | 5200 | 0.5410 | 0.7385 | 0.7371 | | 0.5209 | 26.09 | 5400 | 0.5315 | 0.7411 | 0.7395 | | 0.5216 | 27.05 | 5600 | 0.5496 | 0.7348 | 0.7337 | | 0.5192 | 28.02 | 5800 | 0.5236 | 0.7491 | 0.7474 | | 0.5191 | 28.99 | 6000 | 0.5442 | 0.7349 | 0.7337 | | 0.5192 | 29.95 | 6200 | 0.5441 | 0.7361 | 0.7349 | | 0.5226 | 30.92 | 6400 | 0.5269 | 0.7445 | 0.7428 | | 0.5198 | 31.88 | 6600 | 0.5376 | 0.7381 | 0.7368 | | 0.5154 | 32.85 | 6800 | 0.5336 | 0.7425 | 0.7410 | | 0.5185 | 33.82 | 7000 | 0.5451 | 0.7339 | 0.7328 | | 0.5175 | 34.78 | 7200 | 0.5421 | 0.7349 | 0.7337 | | 0.5185 | 35.75 | 7400 | 0.5347 | 0.7412 | 0.7398 | | 0.5142 | 36.71 | 7600 | 0.5356 | 0.7397 | 0.7383 | | 0.5169 | 37.68 | 7800 | 0.5328 | 0.7410 | 0.7395 | | 0.5151 | 38.65 | 8000 | 0.5274 | 0.7457 | 0.7440 | | 0.5189 | 39.61 | 8200 | 0.5351 | 0.7427 | 0.7413 | | 0.5132 | 40.58 | 8400 | 0.5431 | 0.7351 | 0.7340 | | 0.5111 | 41.55 | 8600 | 0.5349 | 0.7418 | 0.7404 | | 0.5158 | 42.51 | 8800 | 0.5389 | 0.7414 | 0.7401 | | 0.5162 | 43.48 | 9000 | 0.5436 | 0.7370 | 0.7359 | | 0.5141 | 44.44 | 9200 | 0.5415 | 0.7371 | 0.7359 | | 0.5164 | 45.41 | 9400 | 0.5357 | 0.7412 | 0.7398 | | 0.5098 | 46.38 | 9600 | 0.5421 | 0.7377 | 0.7365 | | 0.5161 | 47.34 | 9800 | 0.5383 | 0.7399 | 0.7386 | | 0.514 | 48.31 | 10000 | 0.5360 | 0.7418 | 0.7404 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_65536_512_47M-L1_f

2024-05-03T15:27:51+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K14ac-seqsight\_65536\_512\_47M-L1\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.5178 * F1 Score: 0.7429 * Accuracy: 0.7419 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_all-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.2054 - F1 Score: 0.9157 - Accuracy: 0.9157 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.343 | 0.54 | 200 | 0.2459 | 0.9026 | 0.9027 | | 0.2499 | 1.08 | 400 | 0.2218 | 0.9117 | 0.9118 | | 0.2374 | 1.62 | 600 | 0.2086 | 0.9169 | 0.9169 | | 0.2194 | 2.16 | 800 | 0.2202 | 0.9120 | 0.9122 | | 0.2203 | 2.7 | 1000 | 0.2095 | 0.9157 | 0.9157 | | 0.2117 | 3.24 | 1200 | 0.2133 | 0.9144 | 0.9145 | | 0.2105 | 3.78 | 1400 | 0.1998 | 0.9174 | 0.9174 | | 0.2083 | 4.32 | 1600 | 0.1922 | 0.9221 | 0.9221 | | 0.2016 | 4.86 | 1800 | 0.1942 | 0.9230 | 0.9230 | | 0.1972 | 5.41 | 2000 | 0.1966 | 0.9245 | 0.9245 | | 0.1992 | 5.95 | 2200 | 0.1909 | 0.9245 | 0.9245 | | 0.196 | 6.49 | 2400 | 0.1907 | 0.9228 | 0.9228 | | 0.1947 | 7.03 | 2600 | 0.1882 | 0.9258 | 0.9258 | | 0.1873 | 7.57 | 2800 | 0.1886 | 0.9260 | 0.9260 | | 0.1925 | 8.11 | 3000 | 0.1872 | 0.9274 | 0.9274 | | 0.1857 | 8.65 | 3200 | 0.1914 | 0.9262 | 0.9262 | | 0.1805 | 9.19 | 3400 | 0.1913 | 0.9260 | 0.9260 | | 0.1843 | 9.73 | 3600 | 0.1856 | 0.9247 | 0.9247 | | 0.1878 | 10.27 | 3800 | 0.1876 | 0.9258 | 0.9258 | | 0.1837 | 10.81 | 4000 | 0.1854 | 0.9285 | 0.9285 | | 0.1854 | 11.35 | 4200 | 0.1864 | 0.9258 | 0.9258 | | 0.1774 | 11.89 | 4400 | 0.1869 | 0.9279 | 0.9279 | | 0.1792 | 12.43 | 4600 | 0.1850 | 0.9252 | 0.9252 | | 0.1781 | 12.97 | 4800 | 0.1885 | 0.9246 | 0.9247 | | 0.1727 | 13.51 | 5000 | 0.1873 | 0.9243 | 0.9243 | | 0.1771 | 14.05 | 5200 | 0.1925 | 0.9223 | 0.9223 | | 0.1702 | 14.59 | 5400 | 0.1903 | 0.9240 | 0.9240 | | 0.1709 | 15.14 | 5600 | 0.1865 | 0.9263 | 0.9264 | | 0.1715 | 15.68 | 5800 | 0.1883 | 0.9245 | 0.9245 | | 0.169 | 16.22 | 6000 | 0.1875 | 0.9262 | 0.9262 | | 0.1701 | 16.76 | 6200 | 0.1864 | 0.9255 | 0.9255 | | 0.169 | 17.3 | 6400 | 0.1851 | 0.9260 | 0.9260 | | 0.1701 | 17.84 | 6600 | 0.1842 | 0.9289 | 0.9289 | | 0.1631 | 18.38 | 6800 | 0.1879 | 0.9253 | 0.9253 | | 0.169 | 18.92 | 7000 | 0.1847 | 0.9262 | 0.9262 | | 0.1655 | 19.46 | 7200 | 0.1858 | 0.9270 | 0.9270 | | 0.166 | 20.0 | 7400 | 0.1846 | 0.9272 | 0.9272 | | 0.1679 | 20.54 | 7600 | 0.1846 | 0.9282 | 0.9282 | | 0.1605 | 21.08 | 7800 | 0.1824 | 0.9275 | 0.9275 | | 0.1617 | 21.62 | 8000 | 0.1855 | 0.9272 | 0.9272 | | 0.1589 | 22.16 | 8200 | 0.1851 | 0.9265 | 0.9265 | | 0.157 | 22.7 | 8400 | 0.1860 | 0.9265 | 0.9265 | | 0.1634 | 23.24 | 8600 | 0.1854 | 0.9277 | 0.9277 | | 0.1597 | 23.78 | 8800 | 0.1849 | 0.9267 | 0.9267 | | 0.1598 | 24.32 | 9000 | 0.1854 | 0.9253 | 0.9253 | | 0.1561 | 24.86 | 9200 | 0.1864 | 0.9255 | 0.9255 | | 0.1603 | 25.41 | 9400 | 0.1847 | 0.9260 | 0.9260 | | 0.1571 | 25.95 | 9600 | 0.1854 | 0.9264 | 0.9264 | | 0.16 | 26.49 | 9800 | 0.1848 | 0.9260 | 0.9260 | | 0.1542 | 27.03 | 10000 | 0.1856 | 0.9262 | 0.9262 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_65536_512_47M-L32_f

2024-05-03T15:27:51+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_prom\_prom\_300\_all-seqsight\_65536\_512\_47M-L32\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.2054 * F1 Score: 0.9157 * Accuracy: 0.9157 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K14ac-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5070 - F1 Score: 0.7496 - Accuracy: 0.7492 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5994 | 0.97 | 200 | 0.5606 | 0.7133 | 0.7113 | | 0.5594 | 1.93 | 400 | 0.5410 | 0.7402 | 0.7386 | | 0.551 | 2.9 | 600 | 0.5769 | 0.6998 | 0.7002 | | 0.5454 | 3.86 | 800 | 0.5253 | 0.7506 | 0.7495 | | 0.539 | 4.83 | 1000 | 0.5599 | 0.7288 | 0.7277 | | 0.5356 | 5.8 | 1200 | 0.5610 | 0.7239 | 0.7228 | | 0.5331 | 6.76 | 1400 | 0.5403 | 0.7399 | 0.7383 | | 0.5301 | 7.73 | 1600 | 0.5342 | 0.7452 | 0.7434 | | 0.5223 | 8.7 | 1800 | 0.5390 | 0.7357 | 0.7340 | | 0.5218 | 9.66 | 2000 | 0.5387 | 0.7437 | 0.7422 | | 0.5226 | 10.63 | 2200 | 0.5551 | 0.7298 | 0.7289 | | 0.5135 | 11.59 | 2400 | 0.5250 | 0.7488 | 0.7470 | | 0.5162 | 12.56 | 2600 | 0.5509 | 0.7302 | 0.7292 | | 0.5115 | 13.53 | 2800 | 0.5432 | 0.7315 | 0.7301 | | 0.5094 | 14.49 | 3000 | 0.5460 | 0.7336 | 0.7322 | | 0.5039 | 15.46 | 3200 | 0.5230 | 0.7524 | 0.7507 | | 0.5078 | 16.43 | 3400 | 0.5539 | 0.7267 | 0.7259 | | 0.5061 | 17.39 | 3600 | 0.5226 | 0.7449 | 0.7431 | | 0.5033 | 18.36 | 3800 | 0.5105 | 0.7567 | 0.7555 | | 0.5006 | 19.32 | 4000 | 0.5231 | 0.7458 | 0.7440 | | 0.4992 | 20.29 | 4200 | 0.5260 | 0.7485 | 0.7467 | | 0.4978 | 21.26 | 4400 | 0.5395 | 0.7383 | 0.7368 | | 0.4964 | 22.22 | 4600 | 0.5484 | 0.7364 | 0.7352 | | 0.4961 | 23.19 | 4800 | 0.5210 | 0.7488 | 0.7470 | | 0.4953 | 24.15 | 5000 | 0.5275 | 0.7466 | 0.7449 | | 0.4911 | 25.12 | 5200 | 0.5454 | 0.7352 | 0.7340 | | 0.4913 | 26.09 | 5400 | 0.5358 | 0.7450 | 0.7434 | | 0.4942 | 27.05 | 5600 | 0.5541 | 0.7319 | 0.7310 | | 0.4897 | 28.02 | 5800 | 0.5234 | 0.7473 | 0.7455 | | 0.4897 | 28.99 | 6000 | 0.5351 | 0.7412 | 0.7398 | | 0.4886 | 29.95 | 6200 | 0.5397 | 0.7430 | 0.7416 | | 0.4908 | 30.92 | 6400 | 0.5123 | 0.7500 | 0.7483 | | 0.4885 | 31.88 | 6600 | 0.5345 | 0.7449 | 0.7434 | | 0.483 | 32.85 | 6800 | 0.5370 | 0.7433 | 0.7419 | | 0.4866 | 33.82 | 7000 | 0.5405 | 0.7405 | 0.7392 | | 0.4834 | 34.78 | 7200 | 0.5418 | 0.7396 | 0.7383 | | 0.4863 | 35.75 | 7400 | 0.5247 | 0.7497 | 0.7480 | | 0.4788 | 36.71 | 7600 | 0.5355 | 0.7431 | 0.7416 | | 0.4836 | 37.68 | 7800 | 0.5327 | 0.7446 | 0.7431 | | 0.4793 | 38.65 | 8000 | 0.5271 | 0.7439 | 0.7422 | | 0.4859 | 39.61 | 8200 | 0.5266 | 0.7451 | 0.7434 | | 0.4755 | 40.58 | 8400 | 0.5389 | 0.7418 | 0.7404 | | 0.4767 | 41.55 | 8600 | 0.5287 | 0.7442 | 0.7425 | | 0.4806 | 42.51 | 8800 | 0.5347 | 0.7449 | 0.7434 | | 0.482 | 43.48 | 9000 | 0.5420 | 0.7402 | 0.7389 | | 0.4781 | 44.44 | 9200 | 0.5423 | 0.7396 | 0.7383 | | 0.4805 | 45.41 | 9400 | 0.5350 | 0.7422 | 0.7407 | | 0.4742 | 46.38 | 9600 | 0.5426 | 0.7411 | 0.7398 | | 0.4797 | 47.34 | 9800 | 0.5353 | 0.7422 | 0.7407 | | 0.4763 | 48.31 | 10000 | 0.5341 | 0.7419 | 0.7404 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_65536_512_47M-L8_f

2024-05-03T15:30:41+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K14ac-seqsight\_65536\_512\_47M-L8\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.5070 * F1 Score: 0.7496 * Accuracy: 0.7492 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K14ac-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5053 - F1 Score: 0.7519 - Accuracy: 0.7516 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5922 | 0.97 | 200 | 0.5501 | 0.7277 | 0.7259 | | 0.5536 | 1.93 | 400 | 0.5345 | 0.7481 | 0.7464 | | 0.5428 | 2.9 | 600 | 0.5770 | 0.6964 | 0.6974 | | 0.5355 | 3.86 | 800 | 0.5226 | 0.7478 | 0.7461 | | 0.5261 | 4.83 | 1000 | 0.5679 | 0.7220 | 0.7219 | | 0.5212 | 5.8 | 1200 | 0.5490 | 0.7366 | 0.7352 | | 0.5147 | 6.76 | 1400 | 0.5301 | 0.7412 | 0.7395 | | 0.5087 | 7.73 | 1600 | 0.5315 | 0.7408 | 0.7392 | | 0.5006 | 8.7 | 1800 | 0.5362 | 0.7376 | 0.7362 | | 0.4975 | 9.66 | 2000 | 0.5277 | 0.7492 | 0.7477 | | 0.4968 | 10.63 | 2200 | 0.5336 | 0.7426 | 0.7410 | | 0.4849 | 11.59 | 2400 | 0.5264 | 0.7458 | 0.7440 | | 0.4878 | 12.56 | 2600 | 0.5515 | 0.7297 | 0.7286 | | 0.4801 | 13.53 | 2800 | 0.5437 | 0.7329 | 0.7316 | | 0.4766 | 14.49 | 3000 | 0.5312 | 0.7451 | 0.7434 | | 0.4673 | 15.46 | 3200 | 0.5245 | 0.7518 | 0.7501 | | 0.4702 | 16.43 | 3400 | 0.5453 | 0.7350 | 0.7340 | | 0.4663 | 17.39 | 3600 | 0.5189 | 0.7491 | 0.7474 | | 0.4622 | 18.36 | 3800 | 0.5069 | 0.7562 | 0.7552 | | 0.4571 | 19.32 | 4000 | 0.5311 | 0.7521 | 0.7504 | | 0.4544 | 20.29 | 4200 | 0.5329 | 0.7478 | 0.7461 | | 0.4468 | 21.26 | 4400 | 0.5485 | 0.7369 | 0.7356 | | 0.4466 | 22.22 | 4600 | 0.5514 | 0.7444 | 0.7431 | | 0.4437 | 23.19 | 4800 | 0.5269 | 0.7539 | 0.7522 | | 0.4418 | 24.15 | 5000 | 0.5448 | 0.7416 | 0.7401 | | 0.4346 | 25.12 | 5200 | 0.5589 | 0.7397 | 0.7386 | | 0.4328 | 26.09 | 5400 | 0.5513 | 0.7423 | 0.7407 | | 0.4344 | 27.05 | 5600 | 0.5714 | 0.7316 | 0.7310 | | 0.4283 | 28.02 | 5800 | 0.5413 | 0.7482 | 0.7464 | | 0.4276 | 28.99 | 6000 | 0.5391 | 0.7474 | 0.7458 | | 0.4238 | 29.95 | 6200 | 0.5464 | 0.7449 | 0.7434 | | 0.4231 | 30.92 | 6400 | 0.5280 | 0.7523 | 0.7507 | | 0.4184 | 31.88 | 6600 | 0.5462 | 0.7505 | 0.7489 | | 0.4125 | 32.85 | 6800 | 0.5573 | 0.7458 | 0.7443 | | 0.4161 | 33.82 | 7000 | 0.5635 | 0.7429 | 0.7416 | | 0.4108 | 34.78 | 7200 | 0.5556 | 0.7526 | 0.7510 | | 0.41 | 35.75 | 7400 | 0.5480 | 0.7491 | 0.7474 | | 0.4031 | 36.71 | 7600 | 0.5575 | 0.7463 | 0.7446 | | 0.4097 | 37.68 | 7800 | 0.5583 | 0.7422 | 0.7407 | | 0.4019 | 38.65 | 8000 | 0.5512 | 0.7476 | 0.7458 | | 0.4062 | 39.61 | 8200 | 0.5479 | 0.7512 | 0.7495 | | 0.3978 | 40.58 | 8400 | 0.5593 | 0.7444 | 0.7428 | | 0.396 | 41.55 | 8600 | 0.5620 | 0.7484 | 0.7467 | | 0.398 | 42.51 | 8800 | 0.5535 | 0.7458 | 0.7440 | | 0.3994 | 43.48 | 9000 | 0.5706 | 0.7422 | 0.7407 | | 0.3976 | 44.44 | 9200 | 0.5688 | 0.7438 | 0.7422 | | 0.3972 | 45.41 | 9400 | 0.5655 | 0.7435 | 0.7419 | | 0.3904 | 46.38 | 9600 | 0.5751 | 0.7437 | 0.7422 | | 0.3972 | 47.34 | 9800 | 0.5643 | 0.7417 | 0.7401 | | 0.3917 | 48.31 | 10000 | 0.5639 | 0.7430 | 0.7413 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_65536_512_47M-L32_f

2024-05-03T15:31:21+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K14ac-seqsight\_65536\_512\_47M-L32\_f ================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.5053 * F1 Score: 0.7519 * Accuracy: 0.7516 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

cilantro9246/av4ccn4

2024-05-03T15:32:39+00:00

TAGS #transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # prompt_fine_tuned_CB_bert This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.3050 - Accuracy: 0.3182 - F1: 0.1536 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 400 ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1"], "base_model": "google-bert/bert-base-uncased", "model-index": [{"name": "prompt_fine_tuned_CB_bert", "results": []}]}

tjasad/prompt_fine_tuned_CB_bert

2024-05-03T15:32:41+00:00

TAGS #peft #tensorboard #safetensors #generated_from_trainer #base_model-google-bert/bert-base-uncased #license-apache-2.0 #region-us

# prompt_fine_tuned_CB_bert This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.3050 - Accuracy: 0.3182 - F1: 0.1536 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 400 ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

text-generation

transformers

# bunnycore/Cognitron-8B AWQ - Model creator: [bunnycore](https://huggingface.co/bunnycore) - Original model: [Cognitron-8B](https://huggingface.co/bunnycore/Cognitron-8B) ## How to use ### Install the necessary packages ```bash pip install --upgrade autoawq autoawq-kernels ``` ### Example Python code ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer, TextStreamer model_path = "solidrust/Cognitron-8B-AWQ" system_message = "You are Cognitron-8B, incarnated as a powerful AI. You were created by bunnycore." # Load model model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Convert prompt to tokens prompt_template = """\ <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant""" prompt = "You're standing on the surface of the Earth. "\ "You walk one mile south, one mile west and one mile north. "\ "You end up exactly where you started. Where are you?" tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt), return_tensors='pt').input_ids.cuda() # Generate output generation_output = model.generate(tokens, streamer=streamer, max_new_tokens=512) ``` ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code

{"library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"}

solidrust/Cognitron-8B-AWQ

2024-05-03T15:35:21+00:00

TAGS #transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #conversational #text-generation-inference #region-us

# bunnycore/Cognitron-8B AWQ - Model creator: bunnycore - Original model: Cognitron-8B ## How to use ### Install the necessary packages ### Example Python code ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - Text Generation Webui - using Loader: AutoAWQ - vLLM - version 0.2.2 or later for support for all model types. - Hugging Face Text Generation Inference (TGI) - Transformers version 4.35.0 and later, from any code or client that supports Transformers - AutoAWQ - for use from Python code

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": ["trl", "sft"]}

JamesKim/mistral-7b-qlora-alpaca-sample-0.5k

2024-05-03T15:35:45+00:00

TAGS #transformers #safetensors #mistral #text-generation #trl #sft #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

# bunnycore/LuminariX-8B AWQ - Model creator: [bunnycore](https://huggingface.co/bunnycore) - Original model: [LuminariX-8B](https://huggingface.co/bunnycore/LuminariX-8B) ## How to use ### Install the necessary packages ```bash pip install --upgrade autoawq autoawq-kernels ``` ### Example Python code ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer, TextStreamer model_path = "solidrust/LuminariX-8B-AWQ" system_message = "You are LuminariX-8B, incarnated as a powerful AI. You were created by bunnycore." # Load model model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Convert prompt to tokens prompt_template = """\ <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant""" prompt = "You're standing on the surface of the Earth. "\ "You walk one mile south, one mile west and one mile north. "\ "You end up exactly where you started. Where are you?" tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt), return_tensors='pt').input_ids.cuda() # Generate output generation_output = model.generate(tokens, streamer=streamer, max_new_tokens=512) ``` ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code

{"library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"}

solidrust/LuminariX-8B-AWQ

2024-05-03T15:35:48+00:00

TAGS #transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #conversational #text-generation-inference #region-us

# bunnycore/LuminariX-8B AWQ - Model creator: bunnycore - Original model: LuminariX-8B ## How to use ### Install the necessary packages ### Example Python code ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - Text Generation Webui - using Loader: AutoAWQ - vLLM - version 0.2.2 or later for support for all model types. - Hugging Face Text Generation Inference (TGI) - Transformers version 4.35.0 and later, from any code or client that supports Transformers - AutoAWQ - for use from Python code

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

ferrazzipietro/LS_Llama-2-7b-hf_adapters_en.layer1_NoQuant_16_32_0.01_4_5e-05

2024-05-03T15:36:17+00:00

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

# jsfs11/Llama-3-RPMerge-8B-SLERP AWQ - Model creator: [jsfs11](https://huggingface.co/jsfs11) - Original model: [Llama-3-RPMerge-8B-SLERP](https://huggingface.co/jsfs11/Llama-3-RPMerge-8B-SLERP) ## How to use ### Install the necessary packages ```bash pip install --upgrade autoawq autoawq-kernels ``` ### Example Python code ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer, TextStreamer model_path = "solidrust/Llama-3-RPMerge-8B-SLERP-AWQ" system_message = "You are Llama-3-RPMerge-8B-SLERP, incarnated as a powerful AI. You were created by jsfs11." # Load model model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Convert prompt to tokens prompt_template = """\ <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant""" prompt = "You're standing on the surface of the Earth. "\ "You walk one mile south, one mile west and one mile north. "\ "You end up exactly where you started. Where are you?" tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt), return_tensors='pt').input_ids.cuda() # Generate output generation_output = model.generate(tokens, streamer=streamer, max_new_tokens=512) ``` ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code

{"library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"}

solidrust/Llama-3-RPMerge-8B-SLERP-AWQ

2024-05-03T15:37:55+00:00

TAGS #transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #conversational #text-generation-inference #region-us

# jsfs11/Llama-3-RPMerge-8B-SLERP AWQ - Model creator: jsfs11 - Original model: Llama-3-RPMerge-8B-SLERP ## How to use ### Install the necessary packages ### Example Python code ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - Text Generation Webui - using Loader: AutoAWQ - vLLM - version 0.2.2 or later for support for all model types. - Hugging Face Text Generation Inference (TGI) - Transformers version 4.35.0 and later, from any code or client that supports Transformers - AutoAWQ - for use from Python code

transformers

# Training CLI `Epoch = 0, Global Step = 1000` ```bash python pretrain_our.py \ --accelerator "gpu"\ --strategy "ddp" \ --num-gpus 2 \ --train-datapath "/workspace/data/instructions/train/" \ --val-datapath "/workspace/data/instructions/val/" \ --images "/workspace/data/images" \ --output-dir "/workspace/output_data/our_data_pretrain/" \ --max-steps 60500 \ --batch-size 4 \ --valid-batch-size 4 \ --num-workers 12 \ --lr 5e-5 \ --log-every-n-steps 20 \ --val-check-interval 0.5 \ --warmup-steps 4000 \ --checkpoint-steps 1000 \ --accumulate-grad-batches 64 \ --processor-path "chart-rela-ins/pretrain-small-unichart-table-bs64-low-lr" \ --image-size 512 \ --pretrained-vision-encoder "nxquang-al/unichart-base-960-encoder" \ --pretrained-decoder "nxquang-al/unichart-base-960-decoder" \ --wandb-project "Pretrain-ChartReLA-Instruct" \ ```

{"library_name": "transformers", "tags": []}

chart-rela-ins/pretrain-small-our-data-512

2024-05-03T15:38:00+00:00

TAGS #transformers #safetensors #Chart-rela-instruct #endpoints_compatible #region-us

# Training CLI 'Epoch = 0, Global Step = 1000'

# newsletter/dolphin-2.7-mixtral-8x7b-Q6_K-GGUF This model was converted to GGUF format from [`cognitivecomputations/dolphin-2.7-mixtral-8x7b`](https://huggingface.co/cognitivecomputations/dolphin-2.7-mixtral-8x7b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.7-mixtral-8x7b) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo newsletter/dolphin-2.7-mixtral-8x7b-Q6_K-GGUF --model dolphin-2.7-mixtral-8x7b.Q6_K.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo newsletter/dolphin-2.7-mixtral-8x7b-Q6_K-GGUF --model dolphin-2.7-mixtral-8x7b.Q6_K.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m dolphin-2.7-mixtral-8x7b.Q6_K.gguf -n 128 ```

{"language": ["en"], "license": "apache-2.0", "tags": ["llama-cpp", "gguf-my-repo"], "datasets": ["cognitivecomputations/dolphin", "jondurbin/airoboros-2.2.1", "cognitivecomputations/dolphin-coder", "teknium/openhermes", "ise-uiuc/Magicoder-OSS-Instruct-75K", "ise-uiuc/Magicoder-Evol-Instruct-110K", "LDJnr/Capybara"]}

newsletter/dolphin-2.7-mixtral-8x7b-Q6_K-GGUF

2024-05-03T15:38:18+00:00

TAGS #gguf #llama-cpp #gguf-my-repo #en #dataset-cognitivecomputations/dolphin #dataset-jondurbin/airoboros-2.2.1 #dataset-cognitivecomputations/dolphin-coder #dataset-teknium/openhermes #dataset-ise-uiuc/Magicoder-OSS-Instruct-75K #dataset-ise-uiuc/Magicoder-Evol-Instruct-110K #dataset-LDJnr/Capybara #license-apache-2.0 #region-us

# newsletter/dolphin-2.7-mixtral-8x7b-Q6_K-GGUF This model was converted to GGUF format from 'cognitivecomputations/dolphin-2.7-mixtral-8x7b' using URL via the URL's GGUF-my-repo space. Refer to the original model card for more details on the model. ## Use with URL Install URL through brew. Invoke the URL server or the CLI. CLI: Server: Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": ["trl", "sft"]}

xandykati98/tobias-0.0.7

2024-05-03T15:38:25+00:00

TAGS #transformers #safetensors #trl #sft #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me2-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me2) dataset. It achieves the following results on the evaluation set: - Loss: 0.5990 - F1 Score: 0.6676 - Accuracy: 0.6699 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6574 | 1.04 | 200 | 0.6313 | 0.6136 | 0.6422 | | 0.6258 | 2.08 | 400 | 0.6313 | 0.6401 | 0.6386 | | 0.6188 | 3.12 | 600 | 0.6171 | 0.6510 | 0.6641 | | 0.6173 | 4.17 | 800 | 0.6158 | 0.6565 | 0.6621 | | 0.6134 | 5.21 | 1000 | 0.6279 | 0.6446 | 0.6422 | | 0.6115 | 6.25 | 1200 | 0.6195 | 0.6514 | 0.6510 | | 0.6056 | 7.29 | 1400 | 0.6373 | 0.6384 | 0.6357 | | 0.6093 | 8.33 | 1600 | 0.6249 | 0.6505 | 0.6484 | | 0.6057 | 9.38 | 1800 | 0.6394 | 0.6354 | 0.6331 | | 0.6056 | 10.42 | 2000 | 0.6266 | 0.6512 | 0.6487 | | 0.6069 | 11.46 | 2200 | 0.6124 | 0.6635 | 0.6637 | | 0.6016 | 12.5 | 2400 | 0.6234 | 0.6524 | 0.6504 | | 0.6017 | 13.54 | 2600 | 0.6150 | 0.6600 | 0.6601 | | 0.6024 | 14.58 | 2800 | 0.6105 | 0.6656 | 0.6673 | | 0.605 | 15.62 | 3000 | 0.6172 | 0.6589 | 0.6582 | | 0.6008 | 16.67 | 3200 | 0.6257 | 0.6545 | 0.6520 | | 0.6006 | 17.71 | 3400 | 0.6157 | 0.6622 | 0.6618 | | 0.5984 | 18.75 | 3600 | 0.6171 | 0.6587 | 0.6579 | | 0.6021 | 19.79 | 3800 | 0.6220 | 0.6570 | 0.6549 | | 0.5964 | 20.83 | 4000 | 0.6339 | 0.6478 | 0.6452 | | 0.6013 | 21.88 | 4200 | 0.6332 | 0.6520 | 0.6494 | | 0.5971 | 22.92 | 4400 | 0.6292 | 0.6523 | 0.6497 | | 0.5993 | 23.96 | 4600 | 0.6297 | 0.6517 | 0.6491 | | 0.5952 | 25.0 | 4800 | 0.6225 | 0.6586 | 0.6566 | | 0.5957 | 26.04 | 5000 | 0.6283 | 0.6581 | 0.6556 | | 0.5965 | 27.08 | 5200 | 0.6259 | 0.6586 | 0.6562 | | 0.5946 | 28.12 | 5400 | 0.6203 | 0.6580 | 0.6559 | | 0.5951 | 29.17 | 5600 | 0.6308 | 0.6556 | 0.6530 | | 0.5904 | 30.21 | 5800 | 0.6357 | 0.6569 | 0.6543 | | 0.5945 | 31.25 | 6000 | 0.6264 | 0.6573 | 0.6549 | | 0.5937 | 32.29 | 6200 | 0.6257 | 0.6552 | 0.6527 | | 0.5945 | 33.33 | 6400 | 0.6320 | 0.6578 | 0.6553 | | 0.5927 | 34.38 | 6600 | 0.6172 | 0.6567 | 0.6553 | | 0.5921 | 35.42 | 6800 | 0.6211 | 0.6565 | 0.6546 | | 0.5927 | 36.46 | 7000 | 0.6172 | 0.6556 | 0.6543 | | 0.5903 | 37.5 | 7200 | 0.6274 | 0.6570 | 0.6546 | | 0.5908 | 38.54 | 7400 | 0.6225 | 0.6592 | 0.6572 | | 0.5951 | 39.58 | 7600 | 0.6206 | 0.6580 | 0.6562 | | 0.5936 | 40.62 | 7800 | 0.6327 | 0.6523 | 0.6497 | | 0.5889 | 41.67 | 8000 | 0.6304 | 0.6559 | 0.6533 | | 0.5886 | 42.71 | 8200 | 0.6182 | 0.6565 | 0.6553 | | 0.5923 | 43.75 | 8400 | 0.6225 | 0.6567 | 0.6546 | | 0.5923 | 44.79 | 8600 | 0.6304 | 0.6574 | 0.6549 | | 0.5882 | 45.83 | 8800 | 0.6232 | 0.6592 | 0.6572 | | 0.5908 | 46.88 | 9000 | 0.6292 | 0.6590 | 0.6566 | | 0.5896 | 47.92 | 9200 | 0.6257 | 0.6589 | 0.6566 | | 0.5894 | 48.96 | 9400 | 0.6247 | 0.6578 | 0.6556 | | 0.5909 | 50.0 | 9600 | 0.6261 | 0.6582 | 0.6559 | | 0.5899 | 51.04 | 9800 | 0.6266 | 0.6582 | 0.6559 | | 0.5878 | 52.08 | 10000 | 0.6260 | 0.6585 | 0.6562 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K4me2-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me2-seqsight_65536_512_47M-L1_f

2024-05-03T15:38:43+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K4me2-seqsight\_65536\_512\_47M-L1\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K4me2 dataset. It achieves the following results on the evaluation set: * Loss: 0.5990 * F1 Score: 0.6676 * Accuracy: 0.6699 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

golf2248/hb6rskh

2024-05-03T15:39:37+00:00

TAGS #transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me2-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me2) dataset. It achieves the following results on the evaluation set: - Loss: 0.5989 - F1 Score: 0.6776 - Accuracy: 0.6787 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6493 | 1.04 | 200 | 0.6218 | 0.6359 | 0.6517 | | 0.618 | 2.08 | 400 | 0.6295 | 0.6434 | 0.6409 | | 0.6121 | 3.12 | 600 | 0.6109 | 0.6545 | 0.6703 | | 0.6118 | 4.17 | 800 | 0.6149 | 0.6554 | 0.6566 | | 0.6065 | 5.21 | 1000 | 0.6162 | 0.6615 | 0.6615 | | 0.6059 | 6.25 | 1200 | 0.6111 | 0.6649 | 0.6670 | | 0.5978 | 7.29 | 1400 | 0.6313 | 0.6494 | 0.6468 | | 0.6006 | 8.33 | 1600 | 0.6238 | 0.6570 | 0.6549 | | 0.5958 | 9.38 | 1800 | 0.6469 | 0.6349 | 0.6334 | | 0.5949 | 10.42 | 2000 | 0.6213 | 0.6577 | 0.6556 | | 0.5961 | 11.46 | 2200 | 0.6095 | 0.6651 | 0.6654 | | 0.588 | 12.5 | 2400 | 0.6218 | 0.6589 | 0.6569 | | 0.5878 | 13.54 | 2600 | 0.6163 | 0.6641 | 0.6634 | | 0.5875 | 14.58 | 2800 | 0.6121 | 0.6602 | 0.6601 | | 0.5912 | 15.62 | 3000 | 0.6253 | 0.6553 | 0.6533 | | 0.5838 | 16.67 | 3200 | 0.6272 | 0.6471 | 0.6445 | | 0.5821 | 17.71 | 3400 | 0.6249 | 0.6573 | 0.6553 | | 0.5821 | 18.75 | 3600 | 0.6106 | 0.6657 | 0.6667 | | 0.5835 | 19.79 | 3800 | 0.6171 | 0.6586 | 0.6575 | | 0.578 | 20.83 | 4000 | 0.6291 | 0.6477 | 0.6452 | | 0.5805 | 21.88 | 4200 | 0.6405 | 0.6397 | 0.6370 | | 0.5773 | 22.92 | 4400 | 0.6260 | 0.6531 | 0.6510 | | 0.5781 | 23.96 | 4600 | 0.6412 | 0.6383 | 0.6357 | | 0.5737 | 25.0 | 4800 | 0.6280 | 0.6525 | 0.6504 | | 0.5732 | 26.04 | 5000 | 0.6363 | 0.6461 | 0.6435 | | 0.5738 | 27.08 | 5200 | 0.6319 | 0.6514 | 0.6491 | | 0.5719 | 28.12 | 5400 | 0.6284 | 0.6510 | 0.6484 | | 0.571 | 29.17 | 5600 | 0.6307 | 0.6480 | 0.6455 | | 0.5645 | 30.21 | 5800 | 0.6387 | 0.6477 | 0.6452 | | 0.5686 | 31.25 | 6000 | 0.6402 | 0.6433 | 0.6406 | | 0.5689 | 32.29 | 6200 | 0.6184 | 0.6587 | 0.6575 | | 0.5696 | 33.33 | 6400 | 0.6361 | 0.6471 | 0.6445 | | 0.5656 | 34.38 | 6600 | 0.6261 | 0.6510 | 0.6487 | | 0.5648 | 35.42 | 6800 | 0.6285 | 0.6504 | 0.6481 | | 0.5649 | 36.46 | 7000 | 0.6246 | 0.6520 | 0.6500 | | 0.5616 | 37.5 | 7200 | 0.6339 | 0.6474 | 0.6448 | | 0.5615 | 38.54 | 7400 | 0.6267 | 0.6528 | 0.6507 | | 0.5666 | 39.58 | 7600 | 0.6201 | 0.6610 | 0.6598 | | 0.5649 | 40.62 | 7800 | 0.6420 | 0.6429 | 0.6403 | | 0.5614 | 41.67 | 8000 | 0.6358 | 0.6465 | 0.6439 | | 0.5578 | 42.71 | 8200 | 0.6235 | 0.6587 | 0.6575 | | 0.5624 | 43.75 | 8400 | 0.6306 | 0.6511 | 0.6487 | | 0.5616 | 44.79 | 8600 | 0.6354 | 0.6467 | 0.6442 | | 0.5565 | 45.83 | 8800 | 0.6300 | 0.6537 | 0.6517 | | 0.5592 | 46.88 | 9000 | 0.6436 | 0.6449 | 0.6422 | | 0.5582 | 47.92 | 9200 | 0.6384 | 0.6471 | 0.6445 | | 0.5591 | 48.96 | 9400 | 0.6321 | 0.6504 | 0.6481 | | 0.5588 | 50.0 | 9600 | 0.6378 | 0.6484 | 0.6458 | | 0.5573 | 51.04 | 9800 | 0.6376 | 0.6484 | 0.6458 | | 0.5543 | 52.08 | 10000 | 0.6375 | 0.6481 | 0.6455 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K4me2-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me2-seqsight_65536_512_47M-L8_f

2024-05-03T15:39:47+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K4me2-seqsight\_65536\_512\_47M-L8\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K4me2 dataset. It achieves the following results on the evaluation set: * Loss: 0.5989 * F1 Score: 0.6776 * Accuracy: 0.6787 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me2-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me2) dataset. It achieves the following results on the evaluation set: - Loss: 0.6070 - F1 Score: 0.6774 - Accuracy: 0.6771 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6444 | 1.04 | 200 | 0.6170 | 0.6461 | 0.6637 | | 0.6147 | 2.08 | 400 | 0.6314 | 0.6462 | 0.6435 | | 0.6088 | 3.12 | 600 | 0.6064 | 0.6637 | 0.6761 | | 0.6071 | 4.17 | 800 | 0.6289 | 0.6504 | 0.6478 | | 0.5978 | 5.21 | 1000 | 0.6093 | 0.6651 | 0.6667 | | 0.5973 | 6.25 | 1200 | 0.6078 | 0.6586 | 0.6592 | | 0.5857 | 7.29 | 1400 | 0.6229 | 0.6583 | 0.6562 | | 0.5872 | 8.33 | 1600 | 0.6244 | 0.6532 | 0.6510 | | 0.58 | 9.38 | 1800 | 0.6370 | 0.6471 | 0.6445 | | 0.5756 | 10.42 | 2000 | 0.6087 | 0.6662 | 0.6673 | | 0.5768 | 11.46 | 2200 | 0.6089 | 0.6688 | 0.6703 | | 0.5659 | 12.5 | 2400 | 0.6176 | 0.6621 | 0.6605 | | 0.5625 | 13.54 | 2600 | 0.6247 | 0.6655 | 0.6650 | | 0.5621 | 14.58 | 2800 | 0.6154 | 0.6607 | 0.6608 | | 0.5625 | 15.62 | 3000 | 0.6327 | 0.6580 | 0.6559 | | 0.55 | 16.67 | 3200 | 0.6281 | 0.6596 | 0.6572 | | 0.548 | 17.71 | 3400 | 0.6396 | 0.6510 | 0.6484 | | 0.5455 | 18.75 | 3600 | 0.6186 | 0.6668 | 0.6670 | | 0.5445 | 19.79 | 3800 | 0.6354 | 0.6645 | 0.6628 | | 0.537 | 20.83 | 4000 | 0.6197 | 0.6705 | 0.6703 | | 0.5366 | 21.88 | 4200 | 0.6574 | 0.6559 | 0.6533 | | 0.5282 | 22.92 | 4400 | 0.6345 | 0.6568 | 0.6553 | | 0.5267 | 23.96 | 4600 | 0.6559 | 0.6504 | 0.6478 | | 0.5205 | 25.0 | 4800 | 0.6550 | 0.6478 | 0.6452 | | 0.5164 | 26.04 | 5000 | 0.6668 | 0.6533 | 0.6507 | | 0.5117 | 27.08 | 5200 | 0.6734 | 0.6517 | 0.6491 | | 0.5105 | 28.12 | 5400 | 0.6513 | 0.6559 | 0.6533 | | 0.5058 | 29.17 | 5600 | 0.6550 | 0.6646 | 0.6624 | | 0.4985 | 30.21 | 5800 | 0.6716 | 0.6542 | 0.6517 | | 0.4999 | 31.25 | 6000 | 0.6891 | 0.6538 | 0.6514 | | 0.4992 | 32.29 | 6200 | 0.6590 | 0.6609 | 0.6588 | | 0.4945 | 33.33 | 6400 | 0.6745 | 0.6600 | 0.6575 | | 0.4904 | 34.38 | 6600 | 0.6598 | 0.6676 | 0.6670 | | 0.4875 | 35.42 | 6800 | 0.6831 | 0.6588 | 0.6562 | | 0.4886 | 36.46 | 7000 | 0.6859 | 0.6581 | 0.6556 | | 0.4826 | 37.5 | 7200 | 0.6826 | 0.6582 | 0.6556 | | 0.4808 | 38.54 | 7400 | 0.6798 | 0.6645 | 0.6621 | | 0.4845 | 39.58 | 7600 | 0.6652 | 0.6602 | 0.6585 | | 0.4802 | 40.62 | 7800 | 0.7005 | 0.6536 | 0.6510 | | 0.4758 | 41.67 | 8000 | 0.6922 | 0.6578 | 0.6553 | | 0.4766 | 42.71 | 8200 | 0.6780 | 0.6592 | 0.6572 | | 0.4742 | 43.75 | 8400 | 0.6825 | 0.6593 | 0.6569 | | 0.4746 | 44.79 | 8600 | 0.6897 | 0.6610 | 0.6585 | | 0.4692 | 45.83 | 8800 | 0.6892 | 0.6640 | 0.6618 | | 0.4678 | 46.88 | 9000 | 0.7106 | 0.6554 | 0.6530 | | 0.4638 | 47.92 | 9200 | 0.6953 | 0.6623 | 0.6598 | | 0.4681 | 48.96 | 9400 | 0.6901 | 0.6628 | 0.6605 | | 0.4648 | 50.0 | 9600 | 0.7065 | 0.6578 | 0.6553 | | 0.4654 | 51.04 | 9800 | 0.7008 | 0.6614 | 0.6588 | | 0.4609 | 52.08 | 10000 | 0.7016 | 0.6624 | 0.6598 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K4me2-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me2-seqsight_65536_512_47M-L32_f

2024-05-03T15:39:47+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K4me2-seqsight\_65536\_512\_47M-L32\_f ================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K4me2 dataset. It achieves the following results on the evaluation set: * Loss: 0.6070 * F1 Score: 0.6774 * Accuracy: 0.6771 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

reinforcement-learning

stable-baselines3

# **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

{"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "235.05 +/- 45.55", "name": "mean_reward", "verified": false}]}]}]}

jonnynd/ppo-LunarLander-v2

2024-05-03T15:40:22+00:00

TAGS #stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us

# PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library. ## Usage (with Stable-baselines3) TODO: Add your code

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

theGhoul21/srl-sft-kto-030524-16bit-v0.1

2024-05-03T15:41:18+00:00

TAGS #transformers #safetensors #mistral #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K9ac-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K9ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K9ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5102 - F1 Score: 0.7548 - Accuracy: 0.7542 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6138 | 1.15 | 200 | 0.5821 | 0.7066 | 0.7060 | | 0.5629 | 2.3 | 400 | 0.5901 | 0.6915 | 0.6938 | | 0.5391 | 3.45 | 600 | 0.6037 | 0.6810 | 0.6862 | | 0.5352 | 4.6 | 800 | 0.5822 | 0.6930 | 0.6967 | | 0.5273 | 5.75 | 1000 | 0.5492 | 0.7255 | 0.7254 | | 0.5237 | 6.9 | 1200 | 0.5536 | 0.7221 | 0.7226 | | 0.521 | 8.05 | 1400 | 0.5490 | 0.7265 | 0.7265 | | 0.5205 | 9.2 | 1600 | 0.5855 | 0.6946 | 0.6995 | | 0.5134 | 10.34 | 1800 | 0.5456 | 0.7300 | 0.7298 | | 0.5174 | 11.49 | 2000 | 0.5498 | 0.7217 | 0.7226 | | 0.5045 | 12.64 | 2200 | 0.5732 | 0.7073 | 0.7103 | | 0.5156 | 13.79 | 2400 | 0.5612 | 0.7117 | 0.7139 | | 0.5094 | 14.94 | 2600 | 0.5516 | 0.7161 | 0.7175 | | 0.5081 | 16.09 | 2800 | 0.5375 | 0.7394 | 0.7391 | | 0.5068 | 17.24 | 3000 | 0.5506 | 0.7258 | 0.7265 | | 0.5049 | 18.39 | 3200 | 0.5590 | 0.7138 | 0.7157 | | 0.506 | 19.54 | 3400 | 0.5404 | 0.7309 | 0.7312 | | 0.5005 | 20.69 | 3600 | 0.5404 | 0.7355 | 0.7355 | | 0.5032 | 21.84 | 3800 | 0.5314 | 0.7386 | 0.7384 | | 0.4988 | 22.99 | 4000 | 0.5417 | 0.7313 | 0.7319 | | 0.5004 | 24.14 | 4200 | 0.5238 | 0.7447 | 0.7442 | | 0.4917 | 25.29 | 4400 | 0.5408 | 0.7399 | 0.7398 | | 0.4995 | 26.44 | 4600 | 0.5404 | 0.7352 | 0.7352 | | 0.496 | 27.59 | 4800 | 0.5422 | 0.7335 | 0.7341 | | 0.4931 | 28.74 | 5000 | 0.5424 | 0.7310 | 0.7319 | | 0.4985 | 29.89 | 5200 | 0.5349 | 0.7394 | 0.7395 | | 0.4906 | 31.03 | 5400 | 0.5500 | 0.7224 | 0.7236 | | 0.493 | 32.18 | 5600 | 0.5265 | 0.7404 | 0.7398 | | 0.4888 | 33.33 | 5800 | 0.5398 | 0.7323 | 0.7326 | | 0.4997 | 34.48 | 6000 | 0.5376 | 0.7359 | 0.7362 | | 0.487 | 35.63 | 6200 | 0.5320 | 0.7459 | 0.7456 | | 0.4934 | 36.78 | 6400 | 0.5306 | 0.7411 | 0.7409 | | 0.4896 | 37.93 | 6600 | 0.5326 | 0.7423 | 0.7420 | | 0.488 | 39.08 | 6800 | 0.5295 | 0.7408 | 0.7406 | | 0.4902 | 40.23 | 7000 | 0.5307 | 0.7392 | 0.7391 | | 0.489 | 41.38 | 7200 | 0.5307 | 0.7418 | 0.7416 | | 0.4893 | 42.53 | 7400 | 0.5347 | 0.7330 | 0.7334 | | 0.4908 | 43.68 | 7600 | 0.5285 | 0.7440 | 0.7438 | | 0.4845 | 44.83 | 7800 | 0.5382 | 0.7326 | 0.7330 | | 0.4878 | 45.98 | 8000 | 0.5326 | 0.7366 | 0.7366 | | 0.4882 | 47.13 | 8200 | 0.5308 | 0.7418 | 0.7416 | | 0.4862 | 48.28 | 8400 | 0.5320 | 0.7411 | 0.7409 | | 0.4862 | 49.43 | 8600 | 0.5304 | 0.7441 | 0.7438 | | 0.4883 | 50.57 | 8800 | 0.5330 | 0.7374 | 0.7373 | | 0.4872 | 51.72 | 9000 | 0.5363 | 0.7324 | 0.7326 | | 0.4849 | 52.87 | 9200 | 0.5370 | 0.7320 | 0.7323 | | 0.4875 | 54.02 | 9400 | 0.5348 | 0.7336 | 0.7337 | | 0.4861 | 55.17 | 9600 | 0.5352 | 0.7347 | 0.7348 | | 0.4843 | 56.32 | 9800 | 0.5317 | 0.7389 | 0.7388 | | 0.4884 | 57.47 | 10000 | 0.5319 | 0.7389 | 0.7388 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K9ac-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K9ac-seqsight_65536_512_47M-L1_f

2024-05-03T15:44:11+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K9ac-seqsight\_65536\_512\_47M-L1\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K9ac dataset. It achieves the following results on the evaluation set: * Loss: 0.5102 * F1 Score: 0.7548 * Accuracy: 0.7542 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

golf2248/sncka7l

2024-05-03T15:44:58+00:00

TAGS #transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

suthawadee/demo_receipt_th_B

2024-05-03T15:45:17+00:00

TAGS #transformers #safetensors #vision-encoder-decoder #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

token-classification

transformers

This is a NER model meant to be used to detect/extract citations from American legal documents. Ignore the widget on the model card page; see below for usage. ## How to Use the Model This model outputs token-level predictions, which should be processed as follows to obtain meaningful labels for each token: ```python from transformers import AutoTokenizer, AutoModelForTokenClassification import torch tokenizer = AutoTokenizer.from_pretrained("ss108/legal-citation-bert") model = AutoModelForTokenClassification.from_pretrained("ss108/legal-citation-bert") text = "Your example text here" inputs = tokenizer(text, return_tensors="pt", padding=True) outputs = model(**inputs) logits = outputs.logits predictions = torch.argmax(logits, dim=-1) tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0]) predicted_labels = [model.config.id2label[p.item()] for p in predictions[0]] components = [] for token, label in zip(tokens, predicted_labels): components.append(f"{token} : {label}") concat = " ; ".join(components) print(concat)

{"license": "mit"}

ss108/legal-citation-bert

2024-05-03T15:46:47+00:00

TAGS #transformers #safetensors #bert #token-classification #license-mit #autotrain_compatible #endpoints_compatible #region-us

This is a NER model meant to be used to detect/extract citations from American legal documents. Ignore the widget on the model card page; see below for usage. ## How to Use the Model This model outputs token-level predictions, which should be processed as follows to obtain meaningful labels for each token: '''python from transformers import AutoTokenizer, AutoModelForTokenClassification import torch tokenizer = AutoTokenizer.from_pretrained("ss108/legal-citation-bert") model = AutoModelForTokenClassification.from_pretrained("ss108/legal-citation-bert") text = "Your example text here" inputs = tokenizer(text, return_tensors="pt", padding=True) outputs = model(inputs) logits = URL predictions = URL(logits, dim=-1) tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0]) predicted_labels = [URL.id2label[p.item()] for p in predictions[0]] components = [] for token, label in zip(tokens, predicted_labels): URL(f"{token} : {label}") concat = " ; ".join(components) print(concat)

object-detection

# Face Detection using YOLOv9 This model was fine tuned on a dataset of over 2390 images containing human heads. The model was fine tuned for 100 epochs with a batch size of 32 on a 2 NVIDIA T4 16GB GPU, it took around 47 minutes for the fine tuning to complete. ## Downstream Tasks - __Head Detection__: This model can directly use this model for head detection or it can be further fine tuned own a custom dataset to improve the prediction capabilities. # Example Usage ```python # load libraries from huggingface_hub import hf_hub_download from ultralytics import YOLO from supervision import Detections from PIL import Image # download model model_path = hf_hub_download(repo_id="Konthee/YOLOv9-Head-Detection", filename="yolov9c_best.pt") # load model model = YOLO(model_path) # inference image_path = "/path/to/image" output = model(Image.open(image_path)) results = Detections.from_ultralytics(output[0]) ``` # Links - __Dataset Source__: [Roboflow Universe](https://universe.roboflow.com/csgo-head-detection/head-datasets/dataset/2#) -

{"license": "agpl-3.0", "tags": ["object-detection", "pytorch", "roboflow-universe", "pickle", "face-detection"], "library": "ultralytics"}

Konthee/YOLOv9-Head-Detection

2024-05-03T15:46:57+00:00

TAGS #object-detection #pytorch #roboflow-universe #pickle #face-detection #license-agpl-3.0 #region-us

# Face Detection using YOLOv9 This model was fine tuned on a dataset of over 2390 images containing human heads. The model was fine tuned for 100 epochs with a batch size of 32 on a 2 NVIDIA T4 16GB GPU, it took around 47 minutes for the fine tuning to complete. ## Downstream Tasks - __Head Detection__: This model can directly use this model for head detection or it can be further fine tuned own a custom dataset to improve the prediction capabilities. # Example Usage # Links - __Dataset Source__: Roboflow Universe -

token-classification

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # my_awesome_wnut_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2743 - Precision: 0.5663 - Recall: 0.3049 - F1: 0.3964 - Accuracy: 0.9419 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 213 | 0.2791 | 0.5763 | 0.2521 | 0.3507 | 0.9387 | | No log | 2.0 | 426 | 0.2743 | 0.5663 | 0.3049 | 0.3964 | 0.9419 | ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["precision", "recall", "f1", "accuracy"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "my_awesome_wnut_model", "results": []}]}

clboetticher/my_awesome_wnut_model

2024-05-03T15:47:03+00:00

TAGS #transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

my\_awesome\_wnut\_model ======================== This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 0.2743 * Precision: 0.5663 * Recall: 0.3049 * F1: 0.3964 * Accuracy: 0.9419 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 16 * eval\_batch\_size: 16 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 2 ### Training results ### Framework versions * Transformers 4.40.1 * Pytorch 2.2.1+cu121 * Datasets 2.19.0 * Tokenizers 0.19.1

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K9ac-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K9ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K9ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.4852 - F1 Score: 0.7718 - Accuracy: 0.7711 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5895 | 1.15 | 200 | 0.5699 | 0.7147 | 0.7150 | | 0.5382 | 2.3 | 400 | 0.6120 | 0.6541 | 0.6653 | | 0.5156 | 3.45 | 600 | 0.5756 | 0.6956 | 0.6995 | | 0.513 | 4.6 | 800 | 0.5493 | 0.7111 | 0.7132 | | 0.5066 | 5.75 | 1000 | 0.5353 | 0.7345 | 0.7344 | | 0.5015 | 6.9 | 1200 | 0.5397 | 0.7247 | 0.7254 | | 0.4991 | 8.05 | 1400 | 0.5352 | 0.7343 | 0.7344 | | 0.4966 | 9.2 | 1600 | 0.5584 | 0.7020 | 0.7067 | | 0.4901 | 10.34 | 1800 | 0.5325 | 0.7333 | 0.7330 | | 0.4921 | 11.49 | 2000 | 0.5237 | 0.7434 | 0.7431 | | 0.4799 | 12.64 | 2200 | 0.5588 | 0.7143 | 0.7175 | | 0.4875 | 13.79 | 2400 | 0.5296 | 0.7369 | 0.7373 | | 0.4819 | 14.94 | 2600 | 0.5217 | 0.7425 | 0.7424 | | 0.4804 | 16.09 | 2800 | 0.5309 | 0.7380 | 0.7384 | | 0.4784 | 17.24 | 3000 | 0.5339 | 0.7348 | 0.7355 | | 0.475 | 18.39 | 3200 | 0.5229 | 0.7408 | 0.7409 | | 0.4758 | 19.54 | 3400 | 0.5184 | 0.7399 | 0.7398 | | 0.4685 | 20.69 | 3600 | 0.5113 | 0.7519 | 0.7513 | | 0.4712 | 21.84 | 3800 | 0.5294 | 0.7325 | 0.7337 | | 0.4671 | 22.99 | 4000 | 0.5377 | 0.7283 | 0.7301 | | 0.4676 | 24.14 | 4200 | 0.5121 | 0.7443 | 0.7438 | | 0.4593 | 25.29 | 4400 | 0.5343 | 0.7448 | 0.7449 | | 0.4661 | 26.44 | 4600 | 0.5208 | 0.7464 | 0.7460 | | 0.4627 | 27.59 | 4800 | 0.5256 | 0.7382 | 0.7388 | | 0.4587 | 28.74 | 5000 | 0.5222 | 0.7422 | 0.7424 | | 0.464 | 29.89 | 5200 | 0.5312 | 0.7368 | 0.7377 | | 0.4558 | 31.03 | 5400 | 0.5272 | 0.7391 | 0.7395 | | 0.4568 | 32.18 | 5600 | 0.5114 | 0.7486 | 0.7481 | | 0.4523 | 33.33 | 5800 | 0.5230 | 0.7484 | 0.7481 | | 0.4617 | 34.48 | 6000 | 0.5153 | 0.7489 | 0.7485 | | 0.4492 | 35.63 | 6200 | 0.5166 | 0.7482 | 0.7478 | | 0.4555 | 36.78 | 6400 | 0.5150 | 0.7504 | 0.7499 | | 0.449 | 37.93 | 6600 | 0.5312 | 0.7376 | 0.7377 | | 0.4487 | 39.08 | 6800 | 0.5149 | 0.7482 | 0.7478 | | 0.4503 | 40.23 | 7000 | 0.5240 | 0.7400 | 0.7402 | | 0.4502 | 41.38 | 7200 | 0.5216 | 0.7419 | 0.7416 | | 0.4492 | 42.53 | 7400 | 0.5213 | 0.7421 | 0.7420 | | 0.4502 | 43.68 | 7600 | 0.5197 | 0.7443 | 0.7442 | | 0.4437 | 44.83 | 7800 | 0.5234 | 0.7436 | 0.7434 | | 0.4474 | 45.98 | 8000 | 0.5170 | 0.7457 | 0.7452 | | 0.4466 | 47.13 | 8200 | 0.5238 | 0.7417 | 0.7416 | | 0.4438 | 48.28 | 8400 | 0.5234 | 0.7437 | 0.7434 | | 0.4425 | 49.43 | 8600 | 0.5233 | 0.7435 | 0.7431 | | 0.4471 | 50.57 | 8800 | 0.5208 | 0.7452 | 0.7449 | | 0.4445 | 51.72 | 9000 | 0.5237 | 0.7423 | 0.7420 | | 0.4425 | 52.87 | 9200 | 0.5282 | 0.7413 | 0.7413 | | 0.4443 | 54.02 | 9400 | 0.5268 | 0.7413 | 0.7413 | | 0.4428 | 55.17 | 9600 | 0.5280 | 0.7421 | 0.7420 | | 0.4394 | 56.32 | 9800 | 0.5226 | 0.7448 | 0.7445 | | 0.4434 | 57.47 | 10000 | 0.5235 | 0.7437 | 0.7434 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K9ac-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K9ac-seqsight_65536_512_47M-L8_f

2024-05-03T15:47:04+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K9ac-seqsight\_65536\_512\_47M-L8\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K9ac dataset. It achieves the following results on the evaluation set: * Loss: 0.4852 * F1 Score: 0.7718 * Accuracy: 0.7711 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K9ac-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K9ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K9ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.4848 - F1 Score: 0.7827 - Accuracy: 0.7823 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5754 | 1.15 | 200 | 0.5823 | 0.6886 | 0.6920 | | 0.5264 | 2.3 | 400 | 0.5889 | 0.6721 | 0.6794 | | 0.5056 | 3.45 | 600 | 0.5484 | 0.7223 | 0.7233 | | 0.5017 | 4.6 | 800 | 0.5254 | 0.7368 | 0.7370 | | 0.4952 | 5.75 | 1000 | 0.5239 | 0.7431 | 0.7427 | | 0.4875 | 6.9 | 1200 | 0.5354 | 0.7330 | 0.7337 | | 0.4836 | 8.05 | 1400 | 0.5274 | 0.7417 | 0.7413 | | 0.48 | 9.2 | 1600 | 0.5288 | 0.7338 | 0.7348 | | 0.4728 | 10.34 | 1800 | 0.5185 | 0.7485 | 0.7481 | | 0.4714 | 11.49 | 2000 | 0.5194 | 0.7445 | 0.7442 | | 0.4601 | 12.64 | 2200 | 0.5263 | 0.7398 | 0.7402 | | 0.4644 | 13.79 | 2400 | 0.5212 | 0.7466 | 0.7467 | | 0.4575 | 14.94 | 2600 | 0.5052 | 0.7561 | 0.7557 | | 0.4554 | 16.09 | 2800 | 0.5246 | 0.7443 | 0.7445 | | 0.4494 | 17.24 | 3000 | 0.5211 | 0.7554 | 0.7553 | | 0.447 | 18.39 | 3200 | 0.5075 | 0.7587 | 0.7582 | | 0.4438 | 19.54 | 3400 | 0.5049 | 0.7608 | 0.7603 | | 0.4347 | 20.69 | 3600 | 0.5061 | 0.7649 | 0.7647 | | 0.4358 | 21.84 | 3800 | 0.5165 | 0.7500 | 0.7499 | | 0.4279 | 22.99 | 4000 | 0.5435 | 0.7384 | 0.7395 | | 0.4285 | 24.14 | 4200 | 0.5099 | 0.7616 | 0.7614 | | 0.4174 | 25.29 | 4400 | 0.5390 | 0.7531 | 0.7528 | | 0.4258 | 26.44 | 4600 | 0.5235 | 0.7645 | 0.7643 | | 0.4164 | 27.59 | 4800 | 0.5163 | 0.7594 | 0.7589 | | 0.4106 | 28.74 | 5000 | 0.5193 | 0.7562 | 0.7557 | | 0.4144 | 29.89 | 5200 | 0.5387 | 0.7511 | 0.7510 | | 0.4051 | 31.03 | 5400 | 0.5326 | 0.7554 | 0.7549 | | 0.4067 | 32.18 | 5600 | 0.5198 | 0.7593 | 0.7589 | | 0.3991 | 33.33 | 5800 | 0.5407 | 0.7597 | 0.7593 | | 0.4046 | 34.48 | 6000 | 0.5261 | 0.7636 | 0.7632 | | 0.3921 | 35.63 | 6200 | 0.5381 | 0.7605 | 0.7600 | | 0.3954 | 36.78 | 6400 | 0.5318 | 0.7561 | 0.7557 | | 0.3898 | 37.93 | 6600 | 0.5434 | 0.7540 | 0.7535 | | 0.3877 | 39.08 | 6800 | 0.5449 | 0.7572 | 0.7567 | | 0.3862 | 40.23 | 7000 | 0.5500 | 0.7540 | 0.7535 | | 0.3856 | 41.38 | 7200 | 0.5429 | 0.7565 | 0.7560 | | 0.3831 | 42.53 | 7400 | 0.5371 | 0.7583 | 0.7578 | | 0.3806 | 43.68 | 7600 | 0.5411 | 0.7568 | 0.7564 | | 0.3743 | 44.83 | 7800 | 0.5551 | 0.7554 | 0.7549 | | 0.3798 | 45.98 | 8000 | 0.5421 | 0.7567 | 0.7564 | | 0.3773 | 47.13 | 8200 | 0.5566 | 0.7536 | 0.7531 | | 0.373 | 48.28 | 8400 | 0.5591 | 0.7547 | 0.7542 | | 0.3702 | 49.43 | 8600 | 0.5535 | 0.7519 | 0.7513 | | 0.3712 | 50.57 | 8800 | 0.5583 | 0.7536 | 0.7531 | | 0.3701 | 51.72 | 9000 | 0.5568 | 0.7540 | 0.7535 | | 0.3664 | 52.87 | 9200 | 0.5637 | 0.7583 | 0.7578 | | 0.3713 | 54.02 | 9400 | 0.5597 | 0.7537 | 0.7531 | | 0.3679 | 55.17 | 9600 | 0.5612 | 0.7562 | 0.7557 | | 0.3637 | 56.32 | 9800 | 0.5585 | 0.7569 | 0.7564 | | 0.3676 | 57.47 | 10000 | 0.5579 | 0.7569 | 0.7564 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K9ac-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K9ac-seqsight_65536_512_47M-L32_f

2024-05-03T15:47:49+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K9ac-seqsight\_65536\_512\_47M-L32\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K9ac dataset. It achieves the following results on the evaluation set: * Loss: 0.4848 * F1 Score: 0.7827 * Accuracy: 0.7823 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-classification

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # robust_llm_pythia-1b_mz-133_EnronSpam_n-its-10-seed-4 This model is a fine-tuned version of [EleutherAI/pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-1b", "model-index": [{"name": "robust_llm_pythia-1b_mz-133_EnronSpam_n-its-10-seed-4", "results": []}]}

AlignmentResearch/robust_llm_pythia-1b_mz-133_EnronSpam_n-its-10-seed-4

2024-05-03T15:47:58+00:00

TAGS #transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-1b #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# robust_llm_pythia-1b_mz-133_EnronSpam_n-its-10-seed-4 This model is a fine-tuned version of EleutherAI/pythia-1b on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.15.2

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

psykick21/distilbert-base-uncased-finetuned-lora-text-classification

2024-05-03T15:49:43+00:00

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-lora-text-classification This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.3129 - Accuracy: {'accuracy': 0.86} ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:-------------------:| | No log | 1.0 | 250 | 0.4795 | {'accuracy': 0.85} | | 0.4131 | 2.0 | 500 | 0.6526 | {'accuracy': 0.851} | | 0.4131 | 3.0 | 750 | 0.6766 | {'accuracy': 0.854} | | 0.2017 | 4.0 | 1000 | 0.9597 | {'accuracy': 0.855} | | 0.2017 | 5.0 | 1250 | 0.9623 | {'accuracy': 0.857} | | 0.1102 | 6.0 | 1500 | 0.9842 | {'accuracy': 0.866} | | 0.1102 | 7.0 | 1750 | 1.1943 | {'accuracy': 0.859} | | 0.023 | 8.0 | 2000 | 1.2874 | {'accuracy': 0.859} | | 0.023 | 9.0 | 2250 | 1.3154 | {'accuracy': 0.859} | | 0.0047 | 10.0 | 2500 | 1.3129 | {'accuracy': 0.86} | ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "distilbert/distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-lora-text-classification", "results": []}]}

psykick21/distilbert-base-uncased-lora-text-classification

2024-05-03T15:49:50+00:00

TAGS #peft #tensorboard #safetensors #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #region-us

distilbert-base-uncased-lora-text-classification ================================================ This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set: * Loss: 1.3129 * Accuracy: {'accuracy': 0.86} Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.001 * train\_batch\_size: 4 * eval\_batch\_size: 4 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 10 ### Training results ### Framework versions * PEFT 0.10.0 * Transformers 4.40.1 * Pytorch 2.2.1+cu121 * Datasets 2.19.0 * Tokenizers 0.19.1

transformers

# Uploaded model - **Developed by:** rvian - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "gguf"], "base_model": "unsloth/llama-3-8b-bnb-4bit"}

rvian/gguf-lora-llama3-midjourney-prompt-generator

2024-05-03T15:49:53+00:00

TAGS #transformers #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us

# Uploaded model - Developed by: rvian - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>

text-generation

transformers

# Uploaded model - **Developed by:** Vishwaksen - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"}

Vishwaksen/llama-3-CounterServer

2024-05-03T15:49:55+00:00

TAGS #transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #conversational #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

# Uploaded model - Developed by: Vishwaksen - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

ferrazzipietro/LS_Llama-2-7b-hf_adapters_en.layer1_NoQuant_16_32_0.01_8_5e-05

2024-05-03T15:51:44+00:00

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) llama-2-ko-7b - bnb 4bits - Model creator: https://huggingface.co/beomi/ - Original model: https://huggingface.co/beomi/llama-2-ko-7b/ Original model description: --- language: - en - ko pipeline_tag: text-generation inference: false tags: - facebook - meta - pytorch - llama - llama-2 - kollama - llama-2-ko --- **Update Log** - 2023.12.27 - New Model is here! Trained with only open-accessible Korean text corpus: https://huggingface.co/beomi/open-llama-2-ko-7b - 2023.10.19 - Fix Tokenizer bug(space not applied when decoding) after `transforemrs>=4.34.0` # **Llama-2-Ko** 🦙🇰🇷 Llama-2-Ko serves as an advanced iteration of Llama 2, benefiting from an expanded vocabulary and the inclusion of a Korean corpus in its further pretraining. Just like its predecessor, Llama-2-Ko operates within the broad range of generative text models that stretch from 7 billion to 70 billion parameters. This repository focuses on the 7B pretrained version, which is tailored to fit the Hugging Face Transformers format. For access to the other models, feel free to consult the index provided below. ## Model Details **Model Developers** Junbum Lee (Beomi) **Variations** Llama-2-Ko will come in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations. **Input** Models input text only. **Output** Models generate text only. **Model Architecture** Llama-2-Ko is an auto-regressive language model that uses an optimized transformer architecture based on Llama-2. ||Training Data|Params|Content Length|GQA|Tokens|LR| |---|---|---|---|---|---|---| |Llama 2|*A new mix of Korean online data*|7B|4k|&#10007;|>40B*|1e^-5| *Plan to train upto 200B tokens **Vocab Expansion** | Model Name | Vocabulary Size | Description | | --- | --- | --- | | Original Llama-2 | 32000 | Sentencepiece BPE | | **Expanded Llama-2-Ko** | 46336 | Sentencepiece BPE. Added Korean vocab and merges | **Tokenizing "안녕하세요, 오늘은 날씨가 좋네요."** | Model | Tokens | | --- | --- | | Llama-2 | `['▁', '안', '<0xEB>', '<0x85>', '<0x95>', '하', '세', '요', ',', '▁', '오', '<0xEB>', '<0x8A>', '<0x98>', '은', '▁', '<0xEB>', '<0x82>', '<0xA0>', '씨', '가', '▁', '<0xEC>', '<0xA2>', '<0x8B>', '<0xEB>', '<0x84>', '<0xA4>', '요']` | | Llama-2-Ko | `['▁안녕', '하세요', ',', '▁오늘은', '▁날', '씨가', '▁좋네요']` | **Tokenizing "Llama 2: Open Foundation and Fine-Tuned Chat Models"** | Model | Tokens | | --- | --- | | Llama-2 | `['▁L', 'l', 'ama', '▁', '2', ':', '▁Open', '▁Foundation', '▁and', '▁Fine', '-', 'T', 'un', 'ed', '▁Ch', 'at', '▁Mod', 'els']` | | Llama-2-Ko | `['▁L', 'l', 'ama', '▁', '2', ':', '▁Open', '▁Foundation', '▁and', '▁Fine', '-', 'T', 'un', 'ed', '▁Ch', 'at', '▁Mod', 'els']` | # **Model Benchmark** ## LM Eval Harness - Korean (polyglot branch) - Used EleutherAI's lm-evaluation-harness https://github.com/EleutherAI/lm-evaluation-harness/tree/polyglot ### NSMC (Acc) - 50000 full test TBD ### COPA (F1) <img src=https://user-images.githubusercontent.com/11323660/255575809-c037bc6e-0566-436a-a6c1-2329ac92187a.png style="max-width: 700px; width: 100%" /> | Model | 0-shot | 5-shot | 10-shot | 50-shot | | --- | --- | --- | --- | --- | | https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5 | 0.6696 | 0.6477 | 0.6419 | 0.6514 | | https://huggingface.co/kakaobrain/kogpt | 0.7345 | 0.7287 | 0.7277 | 0.7479 | | https://huggingface.co/facebook/xglm-7.5B | 0.6723 | 0.6731 | 0.6769 | 0.7119 | | https://huggingface.co/EleutherAI/polyglot-ko-1.3b | 0.7196 | 0.7193 | 0.7204 | 0.7206 | | https://huggingface.co/EleutherAI/polyglot-ko-3.8b | 0.7595 | 0.7608 | 0.7638 | 0.7788 | | https://huggingface.co/EleutherAI/polyglot-ko-5.8b | 0.7745 | 0.7676 | 0.7775 | 0.7887 | | https://huggingface.co/EleutherAI/polyglot-ko-12.8b | 0.7937 | 0.8108 | 0.8037 | 0.8369 | | Llama-2 Original 7B* | 0.562033 | 0.575982 | 0.576216 | 0.595532 | | Llama-2-Ko-7b 20B (10k) | 0.738780 | 0.762639 | 0.780761 | 0.797863 | | Llama-2-Ko-7b 40B (20k) | 0.743630 | 0.792716 | 0.803746 | 0.825944 | *Llama-2 Original 7B used https://huggingface.co/meta-llama/Llama-2-7b-hf (w/o tokenizer updated) ### HellaSwag (F1) <img src=https://user-images.githubusercontent.com/11323660/255576090-a2bfc1ae-d117-44b7-9f7b-262e41179ec1.png style="max-width: 700px; width: 100%" /> | Model | 0-shot | 5-shot | 10-shot | 50-shot | | --- | --- | --- | --- | --- | | https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5 | 0.5243 | 0.5272 | 0.5166 | 0.5352 | | https://huggingface.co/kakaobrain/kogpt | 0.5590 | 0.5833 | 0.5828 | 0.5907 | | https://huggingface.co/facebook/xglm-7.5B | 0.5665 | 0.5689 | 0.5565 | 0.5622 | | https://huggingface.co/EleutherAI/polyglot-ko-1.3b | 0.5247 | 0.5260 | 0.5278 | 0.5427 | | https://huggingface.co/EleutherAI/polyglot-ko-3.8b | 0.5707 | 0.5830 | 0.5670 | 0.5787 | | https://huggingface.co/EleutherAI/polyglot-ko-5.8b | 0.5976 | 0.5998 | 0.5979 | 0.6208 | | https://huggingface.co/EleutherAI/polyglot-ko-12.8b | 0.5954 | 0.6306 | 0.6098 | 0.6118 | | Llama-2 Original 7B* | 0.415390 | 0.431382 | 0.421342 | 0.442003 | | Llama-2-Ko-7b 20B (10k) | 0.451757 | 0.466751 | 0.472607 | 0.482776 | | Llama-2-Ko-7b 40B (20k) | 0.456246 | 0.465665 | 0.469810 | 0.477374 | *Llama-2 Original 7B used https://huggingface.co/meta-llama/Llama-2-7b-hf (w/o tokenizer updated) ### BoolQ (F1) <img src=https://user-images.githubusercontent.com/11323660/255576343-5d847a6f-3b6a-41a7-af37-0f11940a5ea4.png style="max-width: 700px; width: 100%" /> | Model | 0-shot | 5-shot | 10-shot | 50-shot | | --- | --- | --- | --- | --- | | https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5 | 0.3356 | 0.4014 | 0.3640 | 0.3560 | | https://huggingface.co/kakaobrain/kogpt | 0.4514 | 0.5981 | 0.5499 | 0.5202 | | https://huggingface.co/facebook/xglm-7.5B | 0.4464 | 0.3324 | 0.3324 | 0.3324 | | https://huggingface.co/EleutherAI/polyglot-ko-1.3b | 0.3552 | 0.4751 | 0.4109 | 0.4038 | | https://huggingface.co/EleutherAI/polyglot-ko-3.8b | 0.4320 | 0.5263 | 0.4930 | 0.4038 | | https://huggingface.co/EleutherAI/polyglot-ko-5.8b | 0.4356 | 0.5698 | 0.5187 | 0.5236 | | https://huggingface.co/EleutherAI/polyglot-ko-12.8b | 0.4818 | 0.6041 | 0.6289 | 0.6448 | | Llama-2 Original 7B* | 0.352050 | 0.563238 | 0.474788 | 0.419222 | | Llama-2-Ko-7b 20B (10k) | 0.360656 | 0.679743 | 0.680109 | 0.662152 | | Llama-2-Ko-7b 40B (20k) | 0.578640 | 0.697747 | 0.708358 | 0.714423 | *Llama-2 Original 7B used https://huggingface.co/meta-llama/Llama-2-7b-hf (w/o tokenizer updated) ### SentiNeg (F1) <img src=https://user-images.githubusercontent.com/11323660/255576572-b005a81d-fa4d-4709-b48a-f0fe4eed17a3.png style="max-width: 700px; width: 100%" /> | Model | 0-shot | 5-shot | 10-shot | 50-shot | | --- | --- | --- | --- | --- | | https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5 | 0.6065 | 0.6878 | 0.7280 | 0.8413 | | https://huggingface.co/kakaobrain/kogpt | 0.3747 | 0.8942 | 0.9294 | 0.9698 | | https://huggingface.co/facebook/xglm-7.5B | 0.3578 | 0.4471 | 0.3964 | 0.5271 | | https://huggingface.co/EleutherAI/polyglot-ko-1.3b | 0.6790 | 0.6257 | 0.5514 | 0.7851 | | https://huggingface.co/EleutherAI/polyglot-ko-3.8b | 0.4858 | 0.7950 | 0.7320 | 0.7851 | | https://huggingface.co/EleutherAI/polyglot-ko-5.8b | 0.3394 | 0.8841 | 0.8808 | 0.9521 | | https://huggingface.co/EleutherAI/polyglot-ko-12.8b | 0.9117 | 0.9015 | 0.9345 | 0.9723 | | Llama-2 Original 7B* | 0.347502 | 0.529124 | 0.480641 | 0.788457 | | Llama-2-Ko-7b 20B (10k) | 0.485546 | 0.829503 | 0.871141 | 0.851253 | | Llama-2-Ko-7b 40B (20k) | 0.459447 | 0.761079 | 0.727611 | 0.936988 | *Llama-2 Original 7B used https://huggingface.co/meta-llama/Llama-2-7b-hf (w/o tokenizer updated) ## Note for oobabooga/text-generation-webui Remove `ValueError` at `load_tokenizer` function(line 109 or near), in `modules/models.py`. ```python diff --git a/modules/models.py b/modules/models.py index 232d5fa..de5b7a0 100644 --- a/modules/models.py +++ b/modules/models.py @@ -106,7 +106,7 @@ def load_tokenizer(model_name, model): trust_remote_code=shared.args.trust_remote_code, use_fast=False ) - except ValueError: + except: tokenizer = AutoTokenizer.from_pretrained( path_to_model, trust_remote_code=shared.args.trust_remote_code, ``` Since Llama-2-Ko uses FastTokenizer provided by HF tokenizers NOT sentencepiece package, it is required to use `use_fast=True` option when initialize tokenizer. Apple Sillicon does not support BF16 computing, use CPU instead. (BF16 is supported when using NVIDIA GPU) ## Citation ``` @misc {l._junbum_2023, author = { {L. Junbum} }, title = { llama-2-ko-7b (Revision 4a9993e) }, year = 2023, url = { https://huggingface.co/beomi/llama-2-ko-7b }, doi = { 10.57967/hf/1098 }, publisher = { Hugging Face } } ``` ## Acknowledgement The training is supported by [TPU Research Cloud](https://sites.research.google/trc/) program. # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_beomi__llama-2-ko-7b) | Metric | Value | |-----------------------|---------------------------| | Avg. | 39.43 | | ARC (25-shot) | 48.46 | | HellaSwag (10-shot) | 75.28 | | MMLU (5-shot) | 39.56 | | TruthfulQA (0-shot) | 34.49 | | Winogrande (5-shot) | 72.14 | | GSM8K (5-shot) | 1.97 | | DROP (3-shot) | 4.1 |

{}

RichardErkhov/beomi_-_llama-2-ko-7b-4bits

2024-05-03T15:52:33+00:00

TAGS #transformers #safetensors #llama #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us

Quantization made by Richard Erkhov. Github Discord Request more models llama-2-ko-7b - bnb 4bits * Model creator: URL * Original model: URL Original model description: --------------------------- language: * en * ko pipeline\_tag: text-generation inference: false tags: * facebook * meta * pytorch * llama * llama-2 * kollama * llama-2-ko --- Update Log * 2023.12.27 + New Model is here! Trained with only open-accessible Korean text corpus: URL * 2023.10.19 + Fix Tokenizer bug(space not applied when decoding) after 'transforemrs>=4.34.0' Llama-2-Ko 🇰🇷 ============= Llama-2-Ko serves as an advanced iteration of Llama 2, benefiting from an expanded vocabulary and the inclusion of a Korean corpus in its further pretraining. Just like its predecessor, Llama-2-Ko operates within the broad range of generative text models that stretch from 7 billion to 70 billion parameters. This repository focuses on the 7B pretrained version, which is tailored to fit the Hugging Face Transformers format. For access to the other models, feel free to consult the index provided below. Model Details ------------- Model Developers Junbum Lee (Beomi) Variations Llama-2-Ko will come in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations. Input Models input text only. Output Models generate text only. Model Architecture Llama-2-Ko is an auto-regressive language model that uses an optimized transformer architecture based on Llama-2. Vocab Expansion Model Name: Original Llama-2, Vocabulary Size: 32000, Description: Sentencepiece BPE Model Name: Expanded Llama-2-Ko, Vocabulary Size: 46336, Description: Sentencepiece BPE. Added Korean vocab and merges Tokenizing "안녕하세요, 오늘은 날씨가 좋네요." Tokenizing "Llama 2: Open Foundation and Fine-Tuned Chat Models" Model Benchmark =============== LM Eval Harness - Korean (polyglot branch) ------------------------------------------ * Used EleutherAI's lm-evaluation-harness URL ### NSMC (Acc) - 50000 full test TBD ### COPA (F1)  ### HellaSwag (F1)  ### BoolQ (F1)  ### SentiNeg (F1)  Note for oobabooga/text-generation-webui ---------------------------------------- Remove 'ValueError' at 'load\_tokenizer' function(line 109 or near), in 'modules/URL'. Since Llama-2-Ko uses FastTokenizer provided by HF tokenizers NOT sentencepiece package, it is required to use 'use\_fast=True' option when initialize tokenizer. Apple Sillicon does not support BF16 computing, use CPU instead. (BF16 is supported when using NVIDIA GPU) Acknowledgement --------------- The training is supported by TPU Research Cloud program. Open LLM Leaderboard Evaluation Results ======================================= Detailed results can be found here

text-to-image

diffusers

This is a Diffusers-compatible version of [Yiffymix v43 by chilon249](https://civitai.com/models/3671?modelVersionId=453692). See the original page for more information.

{"license": "apache-2.0"}

IDK-ab0ut/newversion

2024-05-03T15:53:08+00:00

TAGS #diffusers #safetensors #license-apache-2.0 #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us

This is a Diffusers-compatible version of Yiffymix v43 by chilon249. See the original page for more information.

sentence-similarity

sentence-transformers

# CarlosMorales/HateSpeechDetector This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('CarlosMorales/HateSpeechDetector') embeddings = model.encode(sentences) print(embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=CarlosMorales/HateSpeechDetector) ## Training The model was trained with the parameters: **DataLoader**: `sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 999 with parameters: ``` {'batch_size': 4} ``` **Loss**: `sentence_transformers.losses.Matryoshka2dLoss.Matryoshka2dLoss` with parameters: ``` {'loss': 'BatchHardSoftMarginTripletLoss', 'n_layers_per_step': 1, 'last_layer_weight': 1.0, 'prior_layers_weight': 1.0, 'kl_div_weight': 1.0, 'kl_temperature': 0.3, 'matryoshka_dims': [1024, 256, 128, 64], 'matryoshka_weights': [1, 1, 1, 1], 'n_dims_per_step': 1} ``` Parameters of the fit()-Method: ``` { "epochs": 2, "evaluation_steps": 0, "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 1e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 200, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->

{"library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity"], "pipeline_tag": "sentence-similarity"}

CarlosMorales/HateSpeechDetector

2024-05-03T15:54:18+00:00

TAGS #sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #endpoints_compatible #region-us

# CarlosMorales/HateSpeechDetector This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search. ## Usage (Sentence-Transformers) Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: ## Evaluation Results For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL ## Training The model was trained with the parameters: DataLoader: 'sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader' of length 999 with parameters: Loss: 'sentence_transformers.losses.Matryoshka2dLoss.Matryoshka2dLoss' with parameters: Parameters of the fit()-Method: ## Full Model Architecture ## Citing & Authors

text-generation

transformers

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) OpenCerebrum-1.0-7b-SFT - bnb 4bits - Model creator: https://huggingface.co/Locutusque/ - Original model: https://huggingface.co/Locutusque/OpenCerebrum-1.0-7b-SFT/ Original model description: --- language: - en license: apache-2.0 tags: - open-source - code - math - chemistry - biology - text-generation - question-answering datasets: - Open-Orca/SlimOrca - glaiveai/glaive-code-assistant - camel-ai/physics - camel-ai/math - camel-ai/chemistry - camel-ai/biology - WizardLM/WizardLM_evol_instruct_V2_196k - microsoft/orca-math-word-problems-200k - grimulkan/theory-of-mind - Vezora/Tested-22k-Python-Alpaca - m-a-p/Code-Feedback - Locutusque/arc-cot - jondurbin/airoboros-2.1 - WizardLM/WizardLM_evol_instruct_70k pipeline_tag: text-generation --- # OpenCerebrum-1.0-7B-SFT OpenCerebrum-1.0-7B-SFT is an open-source language model fine-tuned from the alpindale/Mistral-7B-v0.2-hf base model on a diverse dataset aimed at replicating capabilities of AetherResearch's proprietary Cerebrum model. The model was fine-tuned on approximately 1.2 million examples across 14 datasets spanning coding, math, science, reasoning, and general instruction-following. The goal was to assemble public datasets that could help the model achieve strong performance on benchmarks where Cerebrum excels. ## Model Details - **Base Model:** alpindale/Mistral-7B-v0.2-hf - **Parameters:** 7 billion - **Fine-Tuning Dataset Size:** ~1,200,000 examples - **Fine-Tuning Data:** Amalgamation of 14 public datasets - **Language:** English - **License:** Apache 2.0 ## Intended Use OpenCerebrum-1.0-7B-SFT is intended to be a powerful open-source model for coding, math, science, and general question-answering and text generation tasks. Its diverse fine-tuning data aims to equip it with broad knowledge and reasoning capabilities. However, as an open-source replica trained on a subset of data compared to the original Cerebrum, it may not match Cerebrum's full performance. Additionally, biases and limitations of the fine-tuning data may be reflected in the model's outputs. ## Limitations and Biases - The model may have biases and limitations inherited from its fine-tuning datasets. Thorough testing is needed to characterize these. - With 1.2 million training examples, the fine-tuning data is still limited compared to the proprietary Cerebrum data. - As the model is based on a 7B parameter model, it has computational and memory constraints compared to larger models. ## Training Details The model was fine-tuned on the 14 datasets listed in the Datasets section, totaling approximately 1.2 million examples. Default training hyperparameters were used. In the future, the fine-tuning dataset may be condensed to more closely match the 5,000 example dataset reputedly used for the original Cerebrum model.

{}

RichardErkhov/Locutusque_-_OpenCerebrum-1.0-7b-SFT-4bits

2024-05-03T15:54:25+00:00

TAGS #transformers #safetensors #mistral #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us

Quantization made by Richard Erkhov. Github Discord Request more models OpenCerebrum-1.0-7b-SFT - bnb 4bits - Model creator: URL - Original model: URL Original model description: --- language: - en license: apache-2.0 tags: - open-source - code - math - chemistry - biology - text-generation - question-answering datasets: - Open-Orca/SlimOrca - glaiveai/glaive-code-assistant - camel-ai/physics - camel-ai/math - camel-ai/chemistry - camel-ai/biology - WizardLM/WizardLM_evol_instruct_V2_196k - microsoft/orca-math-word-problems-200k - grimulkan/theory-of-mind - Vezora/Tested-22k-Python-Alpaca - m-a-p/Code-Feedback - Locutusque/arc-cot - jondurbin/airoboros-2.1 - WizardLM/WizardLM_evol_instruct_70k pipeline_tag: text-generation --- # OpenCerebrum-1.0-7B-SFT OpenCerebrum-1.0-7B-SFT is an open-source language model fine-tuned from the alpindale/Mistral-7B-v0.2-hf base model on a diverse dataset aimed at replicating capabilities of AetherResearch's proprietary Cerebrum model. The model was fine-tuned on approximately 1.2 million examples across 14 datasets spanning coding, math, science, reasoning, and general instruction-following. The goal was to assemble public datasets that could help the model achieve strong performance on benchmarks where Cerebrum excels. ## Model Details - Base Model: alpindale/Mistral-7B-v0.2-hf - Parameters: 7 billion - Fine-Tuning Dataset Size: ~1,200,000 examples - Fine-Tuning Data: Amalgamation of 14 public datasets - Language: English - License: Apache 2.0 ## Intended Use OpenCerebrum-1.0-7B-SFT is intended to be a powerful open-source model for coding, math, science, and general question-answering and text generation tasks. Its diverse fine-tuning data aims to equip it with broad knowledge and reasoning capabilities. However, as an open-source replica trained on a subset of data compared to the original Cerebrum, it may not match Cerebrum's full performance. Additionally, biases and limitations of the fine-tuning data may be reflected in the model's outputs. ## Limitations and Biases - The model may have biases and limitations inherited from its fine-tuning datasets. Thorough testing is needed to characterize these. - With 1.2 million training examples, the fine-tuning data is still limited compared to the proprietary Cerebrum data. - As the model is based on a 7B parameter model, it has computational and memory constraints compared to larger models. ## Training Details The model was fine-tuned on the 14 datasets listed in the Datasets section, totaling approximately 1.2 million examples. Default training hyperparameters were used. In the future, the fine-tuning dataset may be condensed to more closely match the 5,000 example dataset reputedly used for the original Cerebrum model.

fill-mask

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

AmalNlal/BERT-MLM-test

2024-05-03T15:55:20+00:00

TAGS #transformers #safetensors #bert #fill-mask #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

text-generation

transformers

# Uploaded model - **Developed by:** pathos00011 - **License:** apache-2.0 - **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl", "sft"], "base_model": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit"}

pathos00011/phi3_finetune_skycity_merged

2024-05-03T15:55:21+00:00

TAGS #transformers #safetensors #mistral #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/Phi-3-mini-4k-instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

# Uploaded model - Developed by: pathos00011 - License: apache-2.0 - Finetuned from model : unsloth/Phi-3-mini-4k-instruct-bnb-4bit This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>

text-classification

transformers

This model is a finetuned version of [```google-bert/bert-base-multilingual-cased```](https://huggingface.co/google-bert/bert-base-multilingual-cased) model in the **Bengali** and **Hindi** languages. The dataset used is a Kaggle Dataset - [Modified-hate-speech-bengali-hindi](https://www.kaggle.com/datasets/abirmondal/modified-hate-speech-bengali-hindi) This model can classify Bengali and Hindi texts into the following 5 classes: - text - defamation - hate - non-hate - violence - vulgar

{"language": ["bn", "hi"], "license": "apache-2.0", "pipeline_tag": "text-classification"}

abirmondalind/bert-base-multilingual-cased-hate-speech-ben-hin

2024-05-03T15:55:21+00:00

TAGS #transformers #safetensors #bert #text-classification #bn #hi #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

This model is a finetuned version of [](URL model in the Bengali and Hindi languages. The dataset used is a Kaggle Dataset - Modified-hate-speech-bengali-hindi This model can classify Bengali and Hindi texts into the following 5 classes: - text - defamation - hate - non-hate - violence - vulgar

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me3-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.6114 - F1 Score: 0.6663 - Accuracy: 0.6660 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6701 | 0.87 | 200 | 0.6527 | 0.6344 | 0.6342 | | 0.6479 | 1.74 | 400 | 0.6424 | 0.6406 | 0.6408 | | 0.6452 | 2.61 | 600 | 0.6365 | 0.6460 | 0.6462 | | 0.6358 | 3.48 | 800 | 0.6301 | 0.6540 | 0.6549 | | 0.6339 | 4.35 | 1000 | 0.6301 | 0.6450 | 0.6508 | | 0.6303 | 5.22 | 1200 | 0.6351 | 0.6481 | 0.6497 | | 0.6271 | 6.09 | 1400 | 0.6262 | 0.6594 | 0.6592 | | 0.6232 | 6.96 | 1600 | 0.6251 | 0.6620 | 0.6617 | | 0.6221 | 7.83 | 1800 | 0.6205 | 0.6576 | 0.6606 | | 0.6208 | 8.7 | 2000 | 0.6192 | 0.6693 | 0.6690 | | 0.6162 | 9.57 | 2200 | 0.6174 | 0.6639 | 0.6636 | | 0.6188 | 10.43 | 2400 | 0.6180 | 0.6668 | 0.6666 | | 0.6173 | 11.3 | 2600 | 0.6222 | 0.6587 | 0.6598 | | 0.6148 | 12.17 | 2800 | 0.6168 | 0.6691 | 0.6687 | | 0.6146 | 13.04 | 3000 | 0.6151 | 0.6636 | 0.6636 | | 0.611 | 13.91 | 3200 | 0.6167 | 0.6650 | 0.6655 | | 0.6099 | 14.78 | 3400 | 0.6162 | 0.6670 | 0.6674 | | 0.6103 | 15.65 | 3600 | 0.6197 | 0.6669 | 0.6677 | | 0.6071 | 16.52 | 3800 | 0.6195 | 0.6659 | 0.6660 | | 0.6096 | 17.39 | 4000 | 0.6151 | 0.6684 | 0.6685 | | 0.6099 | 18.26 | 4200 | 0.6139 | 0.6678 | 0.6677 | | 0.6046 | 19.13 | 4400 | 0.6150 | 0.6681 | 0.6682 | | 0.6061 | 20.0 | 4600 | 0.6119 | 0.6701 | 0.6698 | | 0.6047 | 20.87 | 4800 | 0.6143 | 0.6711 | 0.6709 | | 0.6053 | 21.74 | 5000 | 0.6188 | 0.6678 | 0.6682 | | 0.6061 | 22.61 | 5200 | 0.6134 | 0.6706 | 0.6709 | | 0.604 | 23.48 | 5400 | 0.6213 | 0.6607 | 0.6628 | | 0.6027 | 24.35 | 5600 | 0.6115 | 0.6728 | 0.6726 | | 0.6029 | 25.22 | 5800 | 0.6263 | 0.6553 | 0.6590 | | 0.5992 | 26.09 | 6000 | 0.6206 | 0.6624 | 0.6644 | | 0.6027 | 26.96 | 6200 | 0.6182 | 0.6645 | 0.6660 | | 0.5997 | 27.83 | 6400 | 0.6246 | 0.6590 | 0.6620 | | 0.6009 | 28.7 | 6600 | 0.6138 | 0.6718 | 0.6720 | | 0.6003 | 29.57 | 6800 | 0.6125 | 0.6703 | 0.6704 | | 0.5953 | 30.43 | 7000 | 0.6220 | 0.6619 | 0.6641 | | 0.6015 | 31.3 | 7200 | 0.6160 | 0.6684 | 0.6693 | | 0.601 | 32.17 | 7400 | 0.6215 | 0.6643 | 0.6668 | | 0.5971 | 33.04 | 7600 | 0.6111 | 0.6717 | 0.6720 | | 0.5996 | 33.91 | 7800 | 0.6144 | 0.6699 | 0.6707 | | 0.5968 | 34.78 | 8000 | 0.6138 | 0.6688 | 0.6693 | | 0.599 | 35.65 | 8200 | 0.6123 | 0.6713 | 0.6717 | | 0.5977 | 36.52 | 8400 | 0.6155 | 0.6694 | 0.6704 | | 0.5986 | 37.39 | 8600 | 0.6131 | 0.6705 | 0.6709 | | 0.5948 | 38.26 | 8800 | 0.6166 | 0.6687 | 0.6696 | | 0.5997 | 39.13 | 9000 | 0.6156 | 0.6667 | 0.6679 | | 0.5972 | 40.0 | 9200 | 0.6136 | 0.6703 | 0.6709 | | 0.5966 | 40.87 | 9400 | 0.6116 | 0.6722 | 0.6723 | | 0.5959 | 41.74 | 9600 | 0.6125 | 0.6720 | 0.6723 | | 0.5995 | 42.61 | 9800 | 0.6126 | 0.6705 | 0.6709 | | 0.5948 | 43.48 | 10000 | 0.6128 | 0.6697 | 0.6701 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K4me3-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me3-seqsight_65536_512_47M-L1_f

2024-05-03T15:55:48+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K4me3-seqsight\_65536\_512\_47M-L1\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K4me3 dataset. It achieves the following results on the evaluation set: * Loss: 0.6114 * F1 Score: 0.6663 * Accuracy: 0.6660 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me3-seqsight_65536_512_47M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.6663 - F1 Score: 0.6771 - Accuracy: 0.6780 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6592 | 0.87 | 200 | 0.6369 | 0.6421 | 0.6457 | | 0.6337 | 1.74 | 400 | 0.6275 | 0.6587 | 0.6584 | | 0.6252 | 2.61 | 600 | 0.6200 | 0.6594 | 0.6595 | | 0.613 | 3.48 | 800 | 0.6134 | 0.6701 | 0.6698 | | 0.6054 | 4.35 | 1000 | 0.6184 | 0.6636 | 0.6633 | | 0.6001 | 5.22 | 1200 | 0.6265 | 0.6576 | 0.6609 | | 0.5912 | 6.09 | 1400 | 0.6365 | 0.6454 | 0.6519 | | 0.5848 | 6.96 | 1600 | 0.6207 | 0.6634 | 0.6660 | | 0.581 | 7.83 | 1800 | 0.6178 | 0.6677 | 0.6674 | | 0.5783 | 8.7 | 2000 | 0.6238 | 0.6669 | 0.6679 | | 0.5679 | 9.57 | 2200 | 0.6105 | 0.6672 | 0.6671 | | 0.5667 | 10.43 | 2400 | 0.6234 | 0.6613 | 0.6641 | | 0.562 | 11.3 | 2600 | 0.6186 | 0.6578 | 0.6625 | | 0.5596 | 12.17 | 2800 | 0.6107 | 0.6681 | 0.6687 | | 0.5557 | 13.04 | 3000 | 0.6174 | 0.6617 | 0.6641 | | 0.5504 | 13.91 | 3200 | 0.6233 | 0.6567 | 0.6598 | | 0.5442 | 14.78 | 3400 | 0.6256 | 0.6585 | 0.6606 | | 0.5444 | 15.65 | 3600 | 0.6267 | 0.6614 | 0.6644 | | 0.5355 | 16.52 | 3800 | 0.6271 | 0.6639 | 0.6658 | | 0.5342 | 17.39 | 4000 | 0.6412 | 0.6657 | 0.6677 | | 0.5333 | 18.26 | 4200 | 0.6348 | 0.6611 | 0.6652 | | 0.5293 | 19.13 | 4400 | 0.6347 | 0.6636 | 0.6660 | | 0.523 | 20.0 | 4600 | 0.6234 | 0.6668 | 0.6685 | | 0.522 | 20.87 | 4800 | 0.6389 | 0.6653 | 0.6677 | | 0.5188 | 21.74 | 5000 | 0.6483 | 0.6667 | 0.6682 | | 0.5179 | 22.61 | 5200 | 0.6582 | 0.6634 | 0.6660 | | 0.5134 | 23.48 | 5400 | 0.6561 | 0.6658 | 0.6696 | | 0.5145 | 24.35 | 5600 | 0.6523 | 0.6541 | 0.6587 | | 0.5066 | 25.22 | 5800 | 0.6677 | 0.6527 | 0.6576 | | 0.5006 | 26.09 | 6000 | 0.6763 | 0.6556 | 0.6603 | | 0.5049 | 26.96 | 6200 | 0.6573 | 0.6608 | 0.6649 | | 0.4982 | 27.83 | 6400 | 0.6839 | 0.6404 | 0.6486 | | 0.4976 | 28.7 | 6600 | 0.6357 | 0.6634 | 0.6641 | | 0.4945 | 29.57 | 6800 | 0.6575 | 0.6628 | 0.6658 | | 0.4871 | 30.43 | 7000 | 0.6674 | 0.6618 | 0.6660 | | 0.4923 | 31.3 | 7200 | 0.6584 | 0.6663 | 0.6687 | | 0.4914 | 32.17 | 7400 | 0.6557 | 0.6683 | 0.6698 | | 0.4865 | 33.04 | 7600 | 0.6558 | 0.6622 | 0.6641 | | 0.4872 | 33.91 | 7800 | 0.6583 | 0.6704 | 0.6728 | | 0.4847 | 34.78 | 8000 | 0.6667 | 0.6690 | 0.6707 | | 0.4797 | 35.65 | 8200 | 0.6573 | 0.6662 | 0.6682 | | 0.4807 | 36.52 | 8400 | 0.6602 | 0.6677 | 0.6701 | | 0.483 | 37.39 | 8600 | 0.6677 | 0.6682 | 0.6704 | | 0.4773 | 38.26 | 8800 | 0.6760 | 0.6689 | 0.6723 | | 0.4812 | 39.13 | 9000 | 0.6683 | 0.6662 | 0.6685 | | 0.4781 | 40.0 | 9200 | 0.6686 | 0.6655 | 0.6682 | | 0.4759 | 40.87 | 9400 | 0.6669 | 0.6714 | 0.6728 | | 0.4759 | 41.74 | 9600 | 0.6669 | 0.6660 | 0.6682 | | 0.4774 | 42.61 | 9800 | 0.6704 | 0.6646 | 0.6671 | | 0.4726 | 43.48 | 10000 | 0.6705 | 0.6655 | 0.6679 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K4me3-seqsight_65536_512_47M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me3-seqsight_65536_512_47M-L32_f

2024-05-03T15:56:15+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K4me3-seqsight\_65536\_512\_47M-L32\_f ================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K4me3 dataset. It achieves the following results on the evaluation set: * Loss: 0.6663 * F1 Score: 0.6771 * Accuracy: 0.6780 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me3-seqsight_65536_512_47M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.6128 - F1 Score: 0.6755 - Accuracy: 0.6758 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6646 | 0.87 | 200 | 0.6460 | 0.6341 | 0.6348 | | 0.6409 | 1.74 | 400 | 0.6356 | 0.6566 | 0.6565 | | 0.6347 | 2.61 | 600 | 0.6265 | 0.6603 | 0.6601 | | 0.6245 | 3.48 | 800 | 0.6214 | 0.6628 | 0.6628 | | 0.6198 | 4.35 | 1000 | 0.6206 | 0.6659 | 0.6668 | | 0.6148 | 5.22 | 1200 | 0.6290 | 0.6488 | 0.6514 | | 0.6078 | 6.09 | 1400 | 0.6396 | 0.6447 | 0.65 | | 0.6036 | 6.96 | 1600 | 0.6216 | 0.6625 | 0.6636 | | 0.6009 | 7.83 | 1800 | 0.6125 | 0.6693 | 0.6690 | | 0.5994 | 8.7 | 2000 | 0.6178 | 0.6664 | 0.6671 | | 0.5939 | 9.57 | 2200 | 0.6101 | 0.6667 | 0.6666 | | 0.5953 | 10.43 | 2400 | 0.6177 | 0.6610 | 0.6628 | | 0.5932 | 11.3 | 2600 | 0.6160 | 0.6590 | 0.6622 | | 0.5907 | 12.17 | 2800 | 0.6072 | 0.6721 | 0.6728 | | 0.5883 | 13.04 | 3000 | 0.6083 | 0.6698 | 0.6712 | | 0.5853 | 13.91 | 3200 | 0.6100 | 0.6667 | 0.6685 | | 0.5821 | 14.78 | 3400 | 0.6164 | 0.6612 | 0.6652 | | 0.5834 | 15.65 | 3600 | 0.6137 | 0.6671 | 0.6704 | | 0.5787 | 16.52 | 3800 | 0.6144 | 0.6695 | 0.6715 | | 0.5788 | 17.39 | 4000 | 0.6118 | 0.6669 | 0.6682 | | 0.5797 | 18.26 | 4200 | 0.6121 | 0.6669 | 0.6693 | | 0.5753 | 19.13 | 4400 | 0.6085 | 0.6814 | 0.6821 | | 0.5744 | 20.0 | 4600 | 0.6010 | 0.6796 | 0.6804 | | 0.573 | 20.87 | 4800 | 0.6082 | 0.6772 | 0.6785 | | 0.5724 | 21.74 | 5000 | 0.6168 | 0.6722 | 0.6739 | | 0.5742 | 22.61 | 5200 | 0.6077 | 0.6765 | 0.6783 | | 0.569 | 23.48 | 5400 | 0.6250 | 0.6580 | 0.6644 | | 0.57 | 24.35 | 5600 | 0.6125 | 0.6725 | 0.6739 | | 0.5676 | 25.22 | 5800 | 0.6240 | 0.6636 | 0.6682 | | 0.5648 | 26.09 | 6000 | 0.6231 | 0.6660 | 0.6704 | | 0.5673 | 26.96 | 6200 | 0.6178 | 0.6662 | 0.6709 | | 0.5636 | 27.83 | 6400 | 0.6358 | 0.6504 | 0.6592 | | 0.5653 | 28.7 | 6600 | 0.6123 | 0.6680 | 0.6709 | | 0.5631 | 29.57 | 6800 | 0.6115 | 0.6670 | 0.6696 | | 0.5563 | 30.43 | 7000 | 0.6305 | 0.6578 | 0.6641 | | 0.5639 | 31.3 | 7200 | 0.6135 | 0.6716 | 0.6747 | | 0.5618 | 32.17 | 7400 | 0.6186 | 0.6706 | 0.6742 | | 0.5594 | 33.04 | 7600 | 0.6106 | 0.6702 | 0.6726 | | 0.5621 | 33.91 | 7800 | 0.6122 | 0.6699 | 0.6728 | | 0.5578 | 34.78 | 8000 | 0.6154 | 0.6750 | 0.6774 | | 0.5595 | 35.65 | 8200 | 0.6106 | 0.6709 | 0.6734 | | 0.5574 | 36.52 | 8400 | 0.6148 | 0.6670 | 0.6707 | | 0.5608 | 37.39 | 8600 | 0.6134 | 0.6753 | 0.6777 | | 0.5547 | 38.26 | 8800 | 0.6235 | 0.6643 | 0.6687 | | 0.5594 | 39.13 | 9000 | 0.6160 | 0.6666 | 0.6701 | | 0.5552 | 40.0 | 9200 | 0.6155 | 0.6672 | 0.6704 | | 0.5565 | 40.87 | 9400 | 0.6111 | 0.6748 | 0.6766 | | 0.5547 | 41.74 | 9600 | 0.6129 | 0.6730 | 0.6753 | | 0.5591 | 42.61 | 9800 | 0.6138 | 0.6715 | 0.6742 | | 0.554 | 43.48 | 10000 | 0.6151 | 0.6713 | 0.6742 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H3K4me3-seqsight_65536_512_47M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me3-seqsight_65536_512_47M-L8_f

2024-05-03T15:56:15+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H3K4me3-seqsight\_65536\_512\_47M-L8\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H3K4me3 dataset. It achieves the following results on the evaluation set: * Loss: 0.6128 * F1 Score: 0.6755 * Accuracy: 0.6758 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

text-generation

transformers

# flammenai/flammen-mistral-7B AWQ - Model creator: [flammenai](https://huggingface.co/flammenai) - Original model: [flammen-mistral-7B](https://huggingface.co/flammenai/flammen-mistral-7B) ## How to use ### Install the necessary packages ```bash pip install --upgrade autoawq autoawq-kernels ``` ### Example Python code ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer, TextStreamer model_path = "solidrust/flammen-mistral-7B-AWQ" system_message = "You are flammen-mistral-7B, incarnated as a powerful AI. You were created by flammenai." # Load model model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Convert prompt to tokens prompt_template = """\ <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant""" prompt = "You're standing on the surface of the Earth. "\ "You walk one mile south, one mile west and one mile north. "\ "You end up exactly where you started. Where are you?" tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt), return_tensors='pt').input_ids.cuda() # Generate output generation_output = model.generate(tokens, streamer=streamer, max_new_tokens=512) ``` ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code

{"library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"}

solidrust/flammen-mistral-7B-AWQ

2024-05-03T16:00:19+00:00

TAGS #transformers #safetensors #mistral #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# flammenai/flammen-mistral-7B AWQ - Model creator: flammenai - Original model: flammen-mistral-7B ## How to use ### Install the necessary packages ### Example Python code ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - Text Generation Webui - using Loader: AutoAWQ - vLLM - version 0.2.2 or later for support for all model types. - Hugging Face Text Generation Inference (TGI) - Transformers version 4.35.0 and later, from any code or client that supports Transformers - AutoAWQ - for use from Python code

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # idefics2-8b-docvqa-finetuned-tutorial This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 50 - num_epochs: 2 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.41.0.dev0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "HuggingFaceM4/idefics2-8b", "model-index": [{"name": "idefics2-8b-docvqa-finetuned-tutorial", "results": []}]}

Aricher13/idefics2-8b-docvqa-finetuned-tutorial

2024-05-03T16:00:34+00:00

TAGS #safetensors #generated_from_trainer #base_model-HuggingFaceM4/idefics2-8b #license-apache-2.0 #region-us

# idefics2-8b-docvqa-finetuned-tutorial This model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 50 - num_epochs: 2 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.41.0.dev0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H4-seqsight_65536_512_47M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_65536_512_47M](https://huggingface.co/mahdibaghbanzadeh/seqsight_65536_512_47M) on the [mahdibaghbanzadeh/GUE_EMP_H4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H4) dataset. It achieves the following results on the evaluation set: - Loss: 0.2770 - F1 Score: 0.8912 - Accuracy: 0.8912 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.4085 | 2.17 | 200 | 0.3031 | 0.8858 | 0.8857 | | 0.304 | 4.35 | 400 | 0.2975 | 0.8853 | 0.8850 | | 0.2926 | 6.52 | 600 | 0.2952 | 0.8831 | 0.8830 | | 0.2932 | 8.7 | 800 | 0.2970 | 0.8839 | 0.8836 | | 0.2811 | 10.87 | 1000 | 0.2957 | 0.8838 | 0.8836 | | 0.2777 | 13.04 | 1200 | 0.2961 | 0.8872 | 0.8871 | | 0.2765 | 15.22 | 1400 | 0.2907 | 0.8885 | 0.8884 | | 0.2734 | 17.39 | 1600 | 0.2907 | 0.8878 | 0.8877 | | 0.2697 | 19.57 | 1800 | 0.2911 | 0.8876 | 0.8877 | | 0.2702 | 21.74 | 2000 | 0.2939 | 0.8872 | 0.8871 | | 0.266 | 23.91 | 2200 | 0.2922 | 0.8879 | 0.8877 | | 0.2636 | 26.09 | 2400 | 0.2950 | 0.8859 | 0.8857 | | 0.262 | 28.26 | 2600 | 0.2891 | 0.8905 | 0.8905 | | 0.2594 | 30.43 | 2800 | 0.2878 | 0.8906 | 0.8905 | | 0.2575 | 32.61 | 3000 | 0.2907 | 0.8927 | 0.8925 | | 0.2575 | 34.78 | 3200 | 0.2893 | 0.8926 | 0.8925 | | 0.2526 | 36.96 | 3400 | 0.2916 | 0.8941 | 0.8939 | | 0.2542 | 39.13 | 3600 | 0.2881 | 0.8934 | 0.8932 | | 0.2505 | 41.3 | 3800 | 0.2911 | 0.8941 | 0.8939 | | 0.249 | 43.48 | 4000 | 0.2922 | 0.8919 | 0.8919 | | 0.2527 | 45.65 | 4200 | 0.2908 | 0.8926 | 0.8925 | | 0.2457 | 47.83 | 4400 | 0.2888 | 0.8947 | 0.8946 | | 0.2481 | 50.0 | 4600 | 0.2882 | 0.8953 | 0.8953 | | 0.2459 | 52.17 | 4800 | 0.2871 | 0.8960 | 0.8960 | | 0.2487 | 54.35 | 5000 | 0.2972 | 0.8935 | 0.8932 | | 0.2422 | 56.52 | 5200 | 0.2944 | 0.8928 | 0.8925 | | 0.243 | 58.7 | 5400 | 0.2894 | 0.8927 | 0.8925 | | 0.2441 | 60.87 | 5600 | 0.2947 | 0.8928 | 0.8925 | | 0.2412 | 63.04 | 5800 | 0.2917 | 0.8934 | 0.8932 | | 0.2415 | 65.22 | 6000 | 0.2922 | 0.8948 | 0.8946 | | 0.2425 | 67.39 | 6200 | 0.2951 | 0.8915 | 0.8912 | | 0.2398 | 69.57 | 6400 | 0.2890 | 0.8941 | 0.8939 | | 0.2401 | 71.74 | 6600 | 0.2923 | 0.8921 | 0.8919 | | 0.2404 | 73.91 | 6800 | 0.2920 | 0.8934 | 0.8932 | | 0.2378 | 76.09 | 7000 | 0.2932 | 0.8935 | 0.8932 | | 0.2383 | 78.26 | 7200 | 0.2935 | 0.8921 | 0.8919 | | 0.2374 | 80.43 | 7400 | 0.2897 | 0.8927 | 0.8925 | | 0.2352 | 82.61 | 7600 | 0.2889 | 0.8933 | 0.8932 | | 0.2395 | 84.78 | 7800 | 0.2918 | 0.8921 | 0.8919 | | 0.2371 | 86.96 | 8000 | 0.2893 | 0.8927 | 0.8925 | | 0.238 | 89.13 | 8200 | 0.2924 | 0.8934 | 0.8932 | | 0.2367 | 91.3 | 8400 | 0.2906 | 0.8921 | 0.8919 | | 0.2327 | 93.48 | 8600 | 0.2903 | 0.8913 | 0.8912 | | 0.2353 | 95.65 | 8800 | 0.2911 | 0.8920 | 0.8919 | | 0.2368 | 97.83 | 9000 | 0.2898 | 0.8920 | 0.8919 | | 0.2374 | 100.0 | 9200 | 0.2917 | 0.8921 | 0.8919 | | 0.2362 | 102.17 | 9400 | 0.2895 | 0.8934 | 0.8932 | | 0.2349 | 104.35 | 9600 | 0.2906 | 0.8934 | 0.8932 | | 0.2317 | 106.52 | 9800 | 0.2897 | 0.8941 | 0.8939 | | 0.2331 | 108.7 | 10000 | 0.2901 | 0.8927 | 0.8925 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_65536_512_47M", "model-index": [{"name": "GUE_EMP_H4-seqsight_65536_512_47M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H4-seqsight_65536_512_47M-L1_f

2024-05-03T16:00:35+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_65536_512_47M #region-us

GUE\_EMP\_H4-seqsight\_65536\_512\_47M-L1\_f ============================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_65536\_512\_47M on the mahdibaghbanzadeh/GUE\_EMP\_H4 dataset. It achieves the following results on the evaluation set: * Loss: 0.2770 * F1 Score: 0.8912 * Accuracy: 0.8912 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

peft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # lora_fine_tuned_cb This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.4089 - Accuracy: 0.3182 - F1: 0.1536 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 400 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:| | 0.9467 | 3.5714 | 50 | 1.1690 | 0.3182 | 0.1536 | | 0.7755 | 7.1429 | 100 | 1.2983 | 0.3182 | 0.1536 | | 0.7396 | 10.7143 | 150 | 1.3709 | 0.3182 | 0.1536 | | 0.6894 | 14.2857 | 200 | 1.3939 | 0.3182 | 0.1536 | | 0.7253 | 17.8571 | 250 | 1.4084 | 0.3182 | 0.1536 | | 0.7187 | 21.4286 | 300 | 1.4133 | 0.3182 | 0.1536 | | 0.6998 | 25.0 | 350 | 1.4096 | 0.3182 | 0.1536 | | 0.7152 | 28.5714 | 400 | 1.4089 | 0.3182 | 0.1536 | ### Framework versions - PEFT 0.10.1.dev0 - Transformers 4.40.1 - Pytorch 2.3.0 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1"], "base_model": "google-bert/bert-base-uncased", "model-index": [{"name": "lora_fine_tuned_cb", "results": []}]}

lenatr99/lora_fine_tuned_cb

2024-05-03T16:00:37+00:00

TAGS #peft #safetensors #generated_from_trainer #base_model-google-bert/bert-base-uncased #license-apache-2.0 #region-us

lora\_fine\_tuned\_cb ===================== This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 1.4089 * Accuracy: 0.3182 * F1: 0.1536 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 8 * eval\_batch\_size: 8 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 400 ### Training results ### Framework versions * PEFT 0.10.1.dev0 * Transformers 4.40.1 * Pytorch 2.3.0 * Datasets 2.19.0 * Tokenizers 0.19.1

text-generation

transformers

# cognitivecomputations/dolphin-2.9-llama3-8b-1m AWQ - Model creator: [cognitivecomputations](https://huggingface.co/cognitivecomputations) - Original model: [dolphin-2.9-llama3-8b-1m](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-1m) ## How to use ### Install the necessary packages ```bash pip install --upgrade autoawq autoawq-kernels ``` ### Example Python code ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer, TextStreamer model_path = "solidrust/dolphin-2.9-llama3-8b-1m-AWQ" system_message = "You are dolphin-2.9-llama3-8b-1m, incarnated as a powerful AI. You were created by cognitivecomputations." # Load model model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Convert prompt to tokens prompt_template = """\ <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant""" prompt = "You're standing on the surface of the Earth. "\ "You walk one mile south, one mile west and one mile north. "\ "You end up exactly where you started. Where are you?" tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt), return_tensors='pt').input_ids.cuda() # Generate output generation_output = model.generate(tokens, streamer=streamer, max_new_tokens=512) ``` ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code

{"library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"}

solidrust/dolphin-2.9-llama3-8b-1m-AWQ

2024-05-03T16:01:32+00:00

TAGS #transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #conversational #text-generation-inference #region-us

# cognitivecomputations/dolphin-2.9-llama3-8b-1m AWQ - Model creator: cognitivecomputations - Original model: dolphin-2.9-llama3-8b-1m ## How to use ### Install the necessary packages ### Example Python code ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - Text Generation Webui - using Loader: AutoAWQ - vLLM - version 0.2.2 or later for support for all model types. - Hugging Face Text Generation Inference (TGI) - Transformers version 4.35.0 and later, from any code or client that supports Transformers - AutoAWQ - for use from Python code

text-generation

transformers

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) llama-2-ko-7b - bnb 8bits - Model creator: https://huggingface.co/beomi/ - Original model: https://huggingface.co/beomi/llama-2-ko-7b/ Original model description: --- language: - en - ko pipeline_tag: text-generation inference: false tags: - facebook - meta - pytorch - llama - llama-2 - kollama - llama-2-ko --- **Update Log** - 2023.12.27 - New Model is here! Trained with only open-accessible Korean text corpus: https://huggingface.co/beomi/open-llama-2-ko-7b - 2023.10.19 - Fix Tokenizer bug(space not applied when decoding) after `transforemrs>=4.34.0` # **Llama-2-Ko** 🦙🇰🇷 Llama-2-Ko serves as an advanced iteration of Llama 2, benefiting from an expanded vocabulary and the inclusion of a Korean corpus in its further pretraining. Just like its predecessor, Llama-2-Ko operates within the broad range of generative text models that stretch from 7 billion to 70 billion parameters. This repository focuses on the 7B pretrained version, which is tailored to fit the Hugging Face Transformers format. For access to the other models, feel free to consult the index provided below. ## Model Details **Model Developers** Junbum Lee (Beomi) **Variations** Llama-2-Ko will come in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations. **Input** Models input text only. **Output** Models generate text only. **Model Architecture** Llama-2-Ko is an auto-regressive language model that uses an optimized transformer architecture based on Llama-2. ||Training Data|Params|Content Length|GQA|Tokens|LR| |---|---|---|---|---|---|---| |Llama 2|*A new mix of Korean online data*|7B|4k|&#10007;|>40B*|1e^-5| *Plan to train upto 200B tokens **Vocab Expansion** | Model Name | Vocabulary Size | Description | | --- | --- | --- | | Original Llama-2 | 32000 | Sentencepiece BPE | | **Expanded Llama-2-Ko** | 46336 | Sentencepiece BPE. Added Korean vocab and merges | **Tokenizing "안녕하세요, 오늘은 날씨가 좋네요."** | Model | Tokens | | --- | --- | | Llama-2 | `['▁', '안', '<0xEB>', '<0x85>', '<0x95>', '하', '세', '요', ',', '▁', '오', '<0xEB>', '<0x8A>', '<0x98>', '은', '▁', '<0xEB>', '<0x82>', '<0xA0>', '씨', '가', '▁', '<0xEC>', '<0xA2>', '<0x8B>', '<0xEB>', '<0x84>', '<0xA4>', '요']` | | Llama-2-Ko | `['▁안녕', '하세요', ',', '▁오늘은', '▁날', '씨가', '▁좋네요']` | **Tokenizing "Llama 2: Open Foundation and Fine-Tuned Chat Models"** | Model | Tokens | | --- | --- | | Llama-2 | `['▁L', 'l', 'ama', '▁', '2', ':', '▁Open', '▁Foundation', '▁and', '▁Fine', '-', 'T', 'un', 'ed', '▁Ch', 'at', '▁Mod', 'els']` | | Llama-2-Ko | `['▁L', 'l', 'ama', '▁', '2', ':', '▁Open', '▁Foundation', '▁and', '▁Fine', '-', 'T', 'un', 'ed', '▁Ch', 'at', '▁Mod', 'els']` | # **Model Benchmark** ## LM Eval Harness - Korean (polyglot branch) - Used EleutherAI's lm-evaluation-harness https://github.com/EleutherAI/lm-evaluation-harness/tree/polyglot ### NSMC (Acc) - 50000 full test TBD ### COPA (F1) <img src=https://user-images.githubusercontent.com/11323660/255575809-c037bc6e-0566-436a-a6c1-2329ac92187a.png style="max-width: 700px; width: 100%" /> | Model | 0-shot | 5-shot | 10-shot | 50-shot | | --- | --- | --- | --- | --- | | https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5 | 0.6696 | 0.6477 | 0.6419 | 0.6514 | | https://huggingface.co/kakaobrain/kogpt | 0.7345 | 0.7287 | 0.7277 | 0.7479 | | https://huggingface.co/facebook/xglm-7.5B | 0.6723 | 0.6731 | 0.6769 | 0.7119 | | https://huggingface.co/EleutherAI/polyglot-ko-1.3b | 0.7196 | 0.7193 | 0.7204 | 0.7206 | | https://huggingface.co/EleutherAI/polyglot-ko-3.8b | 0.7595 | 0.7608 | 0.7638 | 0.7788 | | https://huggingface.co/EleutherAI/polyglot-ko-5.8b | 0.7745 | 0.7676 | 0.7775 | 0.7887 | | https://huggingface.co/EleutherAI/polyglot-ko-12.8b | 0.7937 | 0.8108 | 0.8037 | 0.8369 | | Llama-2 Original 7B* | 0.562033 | 0.575982 | 0.576216 | 0.595532 | | Llama-2-Ko-7b 20B (10k) | 0.738780 | 0.762639 | 0.780761 | 0.797863 | | Llama-2-Ko-7b 40B (20k) | 0.743630 | 0.792716 | 0.803746 | 0.825944 | *Llama-2 Original 7B used https://huggingface.co/meta-llama/Llama-2-7b-hf (w/o tokenizer updated) ### HellaSwag (F1) <img src=https://user-images.githubusercontent.com/11323660/255576090-a2bfc1ae-d117-44b7-9f7b-262e41179ec1.png style="max-width: 700px; width: 100%" /> | Model | 0-shot | 5-shot | 10-shot | 50-shot | | --- | --- | --- | --- | --- | | https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5 | 0.5243 | 0.5272 | 0.5166 | 0.5352 | | https://huggingface.co/kakaobrain/kogpt | 0.5590 | 0.5833 | 0.5828 | 0.5907 | | https://huggingface.co/facebook/xglm-7.5B | 0.5665 | 0.5689 | 0.5565 | 0.5622 | | https://huggingface.co/EleutherAI/polyglot-ko-1.3b | 0.5247 | 0.5260 | 0.5278 | 0.5427 | | https://huggingface.co/EleutherAI/polyglot-ko-3.8b | 0.5707 | 0.5830 | 0.5670 | 0.5787 | | https://huggingface.co/EleutherAI/polyglot-ko-5.8b | 0.5976 | 0.5998 | 0.5979 | 0.6208 | | https://huggingface.co/EleutherAI/polyglot-ko-12.8b | 0.5954 | 0.6306 | 0.6098 | 0.6118 | | Llama-2 Original 7B* | 0.415390 | 0.431382 | 0.421342 | 0.442003 | | Llama-2-Ko-7b 20B (10k) | 0.451757 | 0.466751 | 0.472607 | 0.482776 | | Llama-2-Ko-7b 40B (20k) | 0.456246 | 0.465665 | 0.469810 | 0.477374 | *Llama-2 Original 7B used https://huggingface.co/meta-llama/Llama-2-7b-hf (w/o tokenizer updated) ### BoolQ (F1) <img src=https://user-images.githubusercontent.com/11323660/255576343-5d847a6f-3b6a-41a7-af37-0f11940a5ea4.png style="max-width: 700px; width: 100%" /> | Model | 0-shot | 5-shot | 10-shot | 50-shot | | --- | --- | --- | --- | --- | | https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5 | 0.3356 | 0.4014 | 0.3640 | 0.3560 | | https://huggingface.co/kakaobrain/kogpt | 0.4514 | 0.5981 | 0.5499 | 0.5202 | | https://huggingface.co/facebook/xglm-7.5B | 0.4464 | 0.3324 | 0.3324 | 0.3324 | | https://huggingface.co/EleutherAI/polyglot-ko-1.3b | 0.3552 | 0.4751 | 0.4109 | 0.4038 | | https://huggingface.co/EleutherAI/polyglot-ko-3.8b | 0.4320 | 0.5263 | 0.4930 | 0.4038 | | https://huggingface.co/EleutherAI/polyglot-ko-5.8b | 0.4356 | 0.5698 | 0.5187 | 0.5236 | | https://huggingface.co/EleutherAI/polyglot-ko-12.8b | 0.4818 | 0.6041 | 0.6289 | 0.6448 | | Llama-2 Original 7B* | 0.352050 | 0.563238 | 0.474788 | 0.419222 | | Llama-2-Ko-7b 20B (10k) | 0.360656 | 0.679743 | 0.680109 | 0.662152 | | Llama-2-Ko-7b 40B (20k) | 0.578640 | 0.697747 | 0.708358 | 0.714423 | *Llama-2 Original 7B used https://huggingface.co/meta-llama/Llama-2-7b-hf (w/o tokenizer updated) ### SentiNeg (F1) <img src=https://user-images.githubusercontent.com/11323660/255576572-b005a81d-fa4d-4709-b48a-f0fe4eed17a3.png style="max-width: 700px; width: 100%" /> | Model | 0-shot | 5-shot | 10-shot | 50-shot | | --- | --- | --- | --- | --- | | https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5 | 0.6065 | 0.6878 | 0.7280 | 0.8413 | | https://huggingface.co/kakaobrain/kogpt | 0.3747 | 0.8942 | 0.9294 | 0.9698 | | https://huggingface.co/facebook/xglm-7.5B | 0.3578 | 0.4471 | 0.3964 | 0.5271 | | https://huggingface.co/EleutherAI/polyglot-ko-1.3b | 0.6790 | 0.6257 | 0.5514 | 0.7851 | | https://huggingface.co/EleutherAI/polyglot-ko-3.8b | 0.4858 | 0.7950 | 0.7320 | 0.7851 | | https://huggingface.co/EleutherAI/polyglot-ko-5.8b | 0.3394 | 0.8841 | 0.8808 | 0.9521 | | https://huggingface.co/EleutherAI/polyglot-ko-12.8b | 0.9117 | 0.9015 | 0.9345 | 0.9723 | | Llama-2 Original 7B* | 0.347502 | 0.529124 | 0.480641 | 0.788457 | | Llama-2-Ko-7b 20B (10k) | 0.485546 | 0.829503 | 0.871141 | 0.851253 | | Llama-2-Ko-7b 40B (20k) | 0.459447 | 0.761079 | 0.727611 | 0.936988 | *Llama-2 Original 7B used https://huggingface.co/meta-llama/Llama-2-7b-hf (w/o tokenizer updated) ## Note for oobabooga/text-generation-webui Remove `ValueError` at `load_tokenizer` function(line 109 or near), in `modules/models.py`. ```python diff --git a/modules/models.py b/modules/models.py index 232d5fa..de5b7a0 100644 --- a/modules/models.py +++ b/modules/models.py @@ -106,7 +106,7 @@ def load_tokenizer(model_name, model): trust_remote_code=shared.args.trust_remote_code, use_fast=False ) - except ValueError: + except: tokenizer = AutoTokenizer.from_pretrained( path_to_model, trust_remote_code=shared.args.trust_remote_code, ``` Since Llama-2-Ko uses FastTokenizer provided by HF tokenizers NOT sentencepiece package, it is required to use `use_fast=True` option when initialize tokenizer. Apple Sillicon does not support BF16 computing, use CPU instead. (BF16 is supported when using NVIDIA GPU) ## Citation ``` @misc {l._junbum_2023, author = { {L. Junbum} }, title = { llama-2-ko-7b (Revision 4a9993e) }, year = 2023, url = { https://huggingface.co/beomi/llama-2-ko-7b }, doi = { 10.57967/hf/1098 }, publisher = { Hugging Face } } ``` ## Acknowledgement The training is supported by [TPU Research Cloud](https://sites.research.google/trc/) program. # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_beomi__llama-2-ko-7b) | Metric | Value | |-----------------------|---------------------------| | Avg. | 39.43 | | ARC (25-shot) | 48.46 | | HellaSwag (10-shot) | 75.28 | | MMLU (5-shot) | 39.56 | | TruthfulQA (0-shot) | 34.49 | | Winogrande (5-shot) | 72.14 | | GSM8K (5-shot) | 1.97 | | DROP (3-shot) | 4.1 |

{}

RichardErkhov/beomi_-_llama-2-ko-7b-8bits

2024-05-03T16:02:42+00:00

TAGS #transformers #safetensors #llama #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us

Quantization made by Richard Erkhov. Github Discord Request more models llama-2-ko-7b - bnb 8bits * Model creator: URL * Original model: URL Original model description: --------------------------- language: * en * ko pipeline\_tag: text-generation inference: false tags: * facebook * meta * pytorch * llama * llama-2 * kollama * llama-2-ko --- Update Log * 2023.12.27 + New Model is here! Trained with only open-accessible Korean text corpus: URL * 2023.10.19 + Fix Tokenizer bug(space not applied when decoding) after 'transforemrs>=4.34.0' Llama-2-Ko 🇰🇷 ============= Llama-2-Ko serves as an advanced iteration of Llama 2, benefiting from an expanded vocabulary and the inclusion of a Korean corpus in its further pretraining. Just like its predecessor, Llama-2-Ko operates within the broad range of generative text models that stretch from 7 billion to 70 billion parameters. This repository focuses on the 7B pretrained version, which is tailored to fit the Hugging Face Transformers format. For access to the other models, feel free to consult the index provided below. Model Details ------------- Model Developers Junbum Lee (Beomi) Variations Llama-2-Ko will come in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations. Input Models input text only. Output Models generate text only. Model Architecture Llama-2-Ko is an auto-regressive language model that uses an optimized transformer architecture based on Llama-2. Vocab Expansion Model Name: Original Llama-2, Vocabulary Size: 32000, Description: Sentencepiece BPE Model Name: Expanded Llama-2-Ko, Vocabulary Size: 46336, Description: Sentencepiece BPE. Added Korean vocab and merges Tokenizing "안녕하세요, 오늘은 날씨가 좋네요." Tokenizing "Llama 2: Open Foundation and Fine-Tuned Chat Models" Model Benchmark =============== LM Eval Harness - Korean (polyglot branch) ------------------------------------------ * Used EleutherAI's lm-evaluation-harness URL ### NSMC (Acc) - 50000 full test TBD ### COPA (F1)  ### HellaSwag (F1)  ### BoolQ (F1)  ### SentiNeg (F1)  Note for oobabooga/text-generation-webui ---------------------------------------- Remove 'ValueError' at 'load\_tokenizer' function(line 109 or near), in 'modules/URL'. Since Llama-2-Ko uses FastTokenizer provided by HF tokenizers NOT sentencepiece package, it is required to use 'use\_fast=True' option when initialize tokenizer. Apple Sillicon does not support BF16 computing, use CPU instead. (BF16 is supported when using NVIDIA GPU) Acknowledgement --------------- The training is supported by TPU Research Cloud program. Open LLM Leaderboard Evaluation Results ======================================= Detailed results can be found here

text-generation

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

golf2248/uj5jfvc

2024-05-03T16:03:11+00:00

TAGS #transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

mehdisebai/CodeQwen-text-to-rule

2024-05-03T16:03:14+00:00

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact