rag_llama_demo
所属分类:内容生成
开发工具:Jupyter Notebook
文件大小:0KB
下载次数:0
上传日期:2023-07-24 19:03:40
上 传 者:
sh-1993
说明: 使用用于私有LLM的e5向量嵌入模型的Llama模型的检索增强生成(RAG)
(Retrieval Augmented Generation (RAG) for Llama models using e5 vector embedding model for private LLM usage)
文件列表:
Super-Science-December-1930.epub
rag_llama_demo.ipynb
rag_llama_demo.py
requirements.txt
# rag_llama_demo
Retrieval Augmented Generation (RAG) for Llama models using e5 vector embedding model for private LLM usage. Origial blogpost on [brandonharris.io](http://brandonharris.io).
Notebook, raw .py and requirements.txt for reference. Using [llama_index](https://github.com/jerryjliu/llama_index) and [ehartford/Wizard-Vicuna-13B-Uncensored](https://huggingface.co/ehartford/Wizard-Vicuna-13B-Uncensored) for interactive retrieval and [e5](https://huggingface.co/intfloat/e5-large-v2) for embeddings.
The book used as an example in this code and hosted on this repo is public domain and was sourced from [Project Gutenberg](https://www.gutenberg.org/ebooks/30691).
近期下载者:
相关文件:
收藏者: