Update README.md

README.md

@@ -1,19 +1,34 @@
----
-language:
-- en
----
----
----
 
-<!-- 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. -->
+# Rubra Mistral-7B-Instruct-v0.2
 
-# run1_short_20000
+## Model description
+The model is the result of further post-training [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2). It is capable of complex tool/function calling.
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the rubra_train_v1_mistral_short dataset.
+## Training Data
 
+The model was post-trained (freeze tuned & DPO) on a proprietary dataset consisting of diverse function calling, chat, and instruct data.
 
-### Training hyperparameters
+## Evaluation
+
+| Model                              | Function Calling | MMLU  | GPQA  | GSM-8K | MATH  | MT-bench |
+|------------------------------------|------------------|-------|-------|--------|-------|----------|
+| Mistral 7B Instruct v0.2           | -                | 59.27 | 27.68 | 43.21  | 10.30 | 7.50     |
+| Rubra Enhanced Mistral 7B Instruct v0.2 | 69.28%           | 58.90 | 29.91 | 34.12  | 8.36  | 7.36     |
+
+
+## How to use
+
+You can use the model with the Hugging Face `transformers` and the rubra library [rubra-tools](https://github.com/rubra-ai/rubra-tools) as follows:
+
+```
+pip install rubra_tools torch==2.3.0 transformers
+```
+
+```python
+TODO
+```
+
+## Training Hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
@@ -26,9 +41,37 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - num_epochs: 1.0
 
-### Framework versions
+## Framework Versions
 
 - Transformers 4.41.2
 - Pytorch 2.3.1+cu121
 - Datasets 2.19.2
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1
+
+## Limitations and Bias
+
+While the model performs well on a wide range of tasks, it may still produce biased or incorrect outputs. Users should exercise caution and critical judgment when using the model in sensitive or high-stakes applications. The model's outputs are influenced by the data it was trained on, which may contain inherent biases.
+
+## Ethical Considerations
+
+Users should ensure that the deployment of this model adheres to ethical guidelines and consider the potential societal impact of the generated text. Misuse of the model for generating harmful or misleading content is strongly discouraged.
+
+## Acknowledgements
+
+We would like to thank Mistral for the model and LLaMA-Factory for training utilities.
+
+## Contact Information
+
+For questions or comments about the model, please reach out to [the rubra team](mailto:rubra@acorn.io).
+
+## Citation
+
+If you use this work, please cite it as:
+
+@misc{rubra202406mistral7binstructv02,
+title = {Rubra-Mistral-7B-Instruct-v0.2},
+author = {Sanjay Nadhavajhala and Yingbei Tong},
+year = {2024},
+publisher = {Hugging Face},
+howpublished = {\url{https://huggingface.co/rubra-ai/Mistral-7B-Instruct-v0.2}},
+}