metadata

license: mit

SciPhi-SearchAgent-Alpha-7B Model Card

The SciPhi-SearchAgent-Alpha-7B is a Large Language Model (LLM) fine-tuned from Mistral-7B-v0.1. This model underwent a fine-tuning process using retrieval-augmented generation (RAG) over search with a fully synthetic dataset. The objective of this work is to generate accurate and well-cited summaries from a range of search results, providing more accurate answers to user queries. For best results, follow the prompting guidelines below.

SciPhi-AI is available via a free hosted API, though the exposed model can vary. Currently, SciPhi-SearchAgent-Alpha-7B is available. More details can be found in the docs here.

Model Architecture

Base Model: Mistral-7B-v0.1

Architecture Features:

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

Using the Model

It is recommended to use a single search query. The model will return an answer using search results as context.

In order to use the model, you can go to the website https://search.sciphi.ai/, or you can run it locally using the following simple command:

export SCIPHI_API_KEY=MY_SCIPHI_API_KEY
# Use the SciPhi `SearchAgent` for LLM RAG w/ AgentSearch
python -m agent_search.scripts.run_rag run --query="What is Fermat's last theorem?"

See the documentation, linked above, for more information.

References

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
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.
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.
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.