Text Generation
Transformers
PyTorch
English
olmo2
conversational
Inference Endpoints
hamishivi commited on
Commit
463fea2
·
verified ·
1 Parent(s): 2d96dbe

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -4,7 +4,7 @@ language:
4
  - en
5
  pipeline_tag: text-generation
6
  base_model:
7
- - allenai/OLMo2-13B-1124
8
  library_name: transformers
9
  ---
10
 
@@ -36,7 +36,7 @@ The core models released in this batch include the following:
36
  - **Model type:** A model trained on a mix of publicly available, synthetic and human-created datasets.
37
  - **Language(s) (NLP):** Primarily English
38
  - **License:** Apache 2.0
39
- - **Finetuned from model:** allenai/OLMo2-13B-1124
40
 
41
  ### Model Sources
42
 
@@ -84,7 +84,7 @@ The model has not been trained with a specific system prompt in mind.
84
 
85
  ### Bias, Risks, and Limitations
86
 
87
- The OLMo2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
88
  See the Falcon 180B model card for an example of this.
89
 
90
 
@@ -92,7 +92,7 @@ See the Falcon 180B model card for an example of this.
92
 
93
  TODO
94
 
95
- ## Hyperparamters
96
 
97
  SFT:
98
  - **Learning Rate**: 1E-5 (7B), 7.5E-06 (13B)
@@ -105,13 +105,13 @@ SFT:
105
 
106
  ## License and use
107
 
108
- OLMo2 is licensed under the Apache 2.0 license.
109
- OLMo2 is intended for research and educational use.
110
  For more information, please see our [Responsible Use Guidelines](https://allenai.org/responsible-use).
111
 
112
  ## Citation
113
 
114
- If OLMo2 or any of the related materials were helpful to your work, please cite:
115
  ```
116
  TODO
117
  ```
 
4
  - en
5
  pipeline_tag: text-generation
6
  base_model:
7
+ - allenai/OLMo-2-13B-1124
8
  library_name: transformers
9
  ---
10
 
 
36
  - **Model type:** A model trained on a mix of publicly available, synthetic and human-created datasets.
37
  - **Language(s) (NLP):** Primarily English
38
  - **License:** Apache 2.0
39
+ - **Finetuned from model:** allenai/OLMo-2-13B-1124
40
 
41
  ### Model Sources
42
 
 
84
 
85
  ### Bias, Risks, and Limitations
86
 
87
+ The OLMo-2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
88
  See the Falcon 180B model card for an example of this.
89
 
90
 
 
92
 
93
  TODO
94
 
95
+ ## Hyperparameters
96
 
97
  SFT:
98
  - **Learning Rate**: 1E-5 (7B), 7.5E-06 (13B)
 
105
 
106
  ## License and use
107
 
108
+ OLMo-2 is licensed under the Apache 2.0 license.
109
+ OLMo-2 is intended for research and educational use.
110
  For more information, please see our [Responsible Use Guidelines](https://allenai.org/responsible-use).
111
 
112
  ## Citation
113
 
114
+ If OLMo-2 or any of the related materials were helpful to your work, please cite:
115
  ```
116
  TODO
117
  ```