LoneStriker/SciPhi-Mistral-7B-32k-8.0bpw-h6-exl2

SciPhi-Mistral-7B-32k Model Card

License: llama2

The SciPhi-Mistral-7B-32k is a Large Language Model (LLM) fine-tuned from Mistral-7B-v0.1. This model underwent a fine-tuning process over four epochs using more than 1 billion tokens, which include regular instruction tuning data and synthetic textbooks. The objective of this work was to increase the model's scientific reasoning and educational abilities.

Model Architecture

Base Model: Mistral-7B-v0.1

Architecture Features:

• Transformer-based model
• Grouped-Query Attention
• Sliding-Window Attention
• Byte-fallback BPE tokenizer

References

1. Lian, W., Goodson, B., Wang, G., Pentland, E., Cook, A., Vong, C., & Teknium. (2023). MistralOrca: Mistral-7B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset. HuggingFace repository. Link
2. Mukherjee, S., Mitra, A., Jawahar, G., Agarwal, S., Palangi, H., & Awadallah, A. (2023). Orca: Progressive Learning from Complex Explanation Traces of GPT-4. arXiv preprint arXiv:2306.02707.
3. Longpre, S., Hou, L., Vu, T., Webson, A., Chung, H. W., Tay, Y., Zhou, D., Le, Q. V., Zoph, B., Wei, J., & Roberts, A. (2023). The Flan Collection: Designing Data and Methods for Effective Instruction Tuning. arXiv preprint arXiv:2301.13688.
4. Mistral AI. (2023). Model Card for Mistral-7B-v0.1. The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks tested. For full details, please refer to the paper and release blog post. Model Architecture: Transformer with Grouped-Query Attention, Sliding-Window Attention, and Byte-fallback BPE tokenizer. Link

Acknowledgements

Thank you to the AI Alignment Lab, vikp, jph00 and others who contributed to this work.