Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,519 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:7960
+- loss:CoSENTLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: And your phone. Okay do you already have a phone in mind, what
+    you wanted to upgrade to.
+  sentences:
+  - I'm now going to read out some terms and conditions to complete the order.
+  - The same discounts you can have been added as an additional line and do into your
+    account. It needs be entitled to % discount off of the costs.
+  - Thank you and could you please confirm to me what is your full name.
+- source_sentence: 'So glad you''re on the right plan. I will also check your average
+    monthly usage for the past few months. Your usage is only ## gig of mobile data
+    and then the highest one, it''s around ##. Gig of mobile details. So definitely
+    the ## gig of mobile data will if broken.'
+  sentences:
+  - Thank you for calling over to my name is how can I help you.
+  - So the phone that you currently have is that currently a Samsung?
+  - So on that's something that you can they get that the shop and it's at a renewal
+    for our insurance. So just in case like once you get back to the UK and you don't
+    want to have the insurance anymore. You can possibly remove that. That and the
+    full garbage insurance.
+- source_sentence: Okay, well, I just want to share with you that I'm happy to advise
+    that you have an amazing offer on our secondary ninth. So there any family members
+    like to join or to under your name with a same billing address so they will be
+    getting a 20% desk.
+  sentences:
+  - Yes, that's correct for know. Our price is £ and then it won't go down to £ after
+    you apply the discount.
+  - Thank you for calling over to my name is how can I help you.
+  - Checking your account I can see you are on the and you have been paying £ per
+    month. Is that correct?
+- source_sentence: 'I just read to process this I just like to open your account here
+    to see if we can get this eligible for your upgrade for the new iPhone ## so here.'
+  sentences:
+  - I now need to read some insurance disclosures related to the Ultimate Plan you
+    have chosen.
+  - Thank you and could you please confirm to me what is your full name.
+  - I can provide to you . Are you happy to go ahead with this?
+- source_sentence: Okay, and can you provide me your full name please.
+  sentences:
+  - So on that's something that you can they get that the shop and it's at a renewal
+    for our insurance. So just in case like once you get back to the UK and you don't
+    want to have the insurance anymore. You can possibly remove that. That and the
+    full garbage insurance.
+  - You. Okay, so for this one, how do you how do you normally use your mobile data.
+  - You. Okay, so for this one, how do you how do you normally use your mobile data.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts_dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.5177189921265649
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.2603983787734805
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.5608459921843345
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.2595766499932607
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.5641188480826617
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.26039837957858836
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5177189925954635
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.26040366240168195
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.5641188480826617
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.26040366240168195
+      name: Spearman Max
+    - type: pearson_cosine
+      value: 0.4585915541798693
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.24734582807664446
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.5059296028724503
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.2466879170820096
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.506069567328991
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.24734582912817787
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.4585915495841867
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.24734582759867477
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.506069567328991
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.24734582912817787
+      name: Spearman Max
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision fa97f6e7cb1a59073dff9e6b13e2715cf7475ac9 -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("enochlev/xlm-similarity")
+# Run inference
+sentences = [
+    'Okay, and can you provide me your full name please.',
+    'You. Okay, so for this one, how do you how do you normally use your mobile data.',
+    'You. Okay, so for this one, how do you how do you normally use your mobile data.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+* Dataset: `sts_dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.5177     |
+| spearman_cosine    | 0.2604     |
+| pearson_manhattan  | 0.5608     |
+| spearman_manhattan | 0.2596     |
+| pearson_euclidean  | 0.5641     |
+| spearman_euclidean | 0.2604     |
+| pearson_dot        | 0.5177     |
+| spearman_dot       | 0.2604     |
+| pearson_max        | 0.5641     |
+| **spearman_max**   | **0.2604** |
+
+#### Semantic Similarity
+* Dataset: `sts_dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.4586     |
+| spearman_cosine    | 0.2473     |
+| pearson_manhattan  | 0.5059     |
+| spearman_manhattan | 0.2467     |
+| pearson_euclidean  | 0.5061     |
+| spearman_euclidean | 0.2473     |
+| pearson_dot        | 0.4586     |
+| spearman_dot       | 0.2473     |
+| pearson_max        | 0.5061     |
+| **spearman_max**   | **0.2473** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 7,960 training samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                            | text2                                                                              | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                             | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 21.6 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 28.35 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 0.2</li><li>mean: 0.22</li><li>max: 1.0</li></ul> |
+* Samples:
+  | text1                                                                      | text2                                                                                                                                                                                                                                                                                                   | label            |
+  |:---------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>Hello, welcome to O2. My name is __ How can I help you today?</code> | <code>Thank you for calling over to my name is how can I help you.</code>                                                                                                                                                                                                                               | <code>1.0</code> |
+  | <code>Hello, welcome to O2. My name is __ How can I help you today?</code> | <code>So, I'd look into our accessory so for the airbags the one that we have an ongoing promotion right now for the accessories is the airport second generation. So you can. And either by there's like a great if you want to or I can also make it as an instalment for you. If you want to.</code> | <code>0.2</code> |
+  | <code>Hello, welcome to O2. My name is __ How can I help you today?</code> | <code>So on that's something that you can they get that the shop and it's at a renewal for our insurance. So just in case like once you get back to the UK and you don't want to have the insurance anymore. You can possibly remove that. That and the full garbage insurance.</code>                  | <code>0.2</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 1,980 evaluation samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                              | text2                                                                              | label                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 39.04 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 28.35 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 0.2</li><li>mean: 0.22</li><li>max: 1.0</li></ul> |
+* Samples:
+  | text1                                                                                                                                                                                                                                                   | text2                                                                                                                                                                                                                                                                                                   | label            |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>Right perfect. Thank you for passenger security cyber. Now let me go ahead. Then I look for your option to do an upgrade. So you had mentioned that you're wanting to get an upgrade. Can you tell me is it for a devise or a single plan.</code> | <code>Are you planning to get a new sim only plan or a new phone?</code>                                                                                                                                                                                                                                | <code>1.0</code> |
+  | <code>Right perfect. Thank you for passenger security cyber. Now let me go ahead. Then I look for your option to do an upgrade. So you had mentioned that you're wanting to get an upgrade. Can you tell me is it for a devise or a single plan.</code> | <code>So, I'd look into our accessory so for the airbags the one that we have an ongoing promotion right now for the accessories is the airport second generation. So you can. And either by there's like a great if you want to or I can also make it as an instalment for you. If you want to.</code> | <code>0.2</code> |
+  | <code>Right perfect. Thank you for passenger security cyber. Now let me go ahead. Then I look for your option to do an upgrade. So you had mentioned that you're wanting to get an upgrade. Can you tell me is it for a devise or a single plan.</code> | <code>So on that's something that you can they get that the shop and it's at a renewal for our insurance. So just in case like once you get back to the UK and you don't want to have the insurance anymore. You can possibly remove that. That and the full garbage insurance.</code>                  | <code>0.2</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | Validation Loss | sts_dev_spearman_max |
+|:-----:|:----:|:---------------:|:--------------------:|
+| 4.0   | 128  | 0.4041          | 0.2604               |
+| 1.0   | 32   | 0.6357          | 0.2473               |
+
+
+### Framework Versions
+- Python: 3.11.9
+- Sentence Transformers: 3.2.1
+- Transformers: 4.45.2
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.1.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.1",
+    "transformers": "4.45.2",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec473adf01c21c28c3cd12f0480713a687135de5b9956a23b4992ea20ed5d235
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}