Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ language:
|
|
4 |
- en
|
5 |
pipeline_tag: text-generation
|
6 |
base_model:
|
7 |
-
- allenai/
|
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/
|
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
|
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 |
-
##
|
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 |
-
|
109 |
-
|
110 |
For more information, please see our [Responsible Use Guidelines](https://allenai.org/responsible-use).
|
111 |
|
112 |
## Citation
|
113 |
|
114 |
-
If
|
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 |
```
|