Building LLama Banker
Doing RAG for Finance using LLama2. Highly recommend you run this in a GPU accelerated environment. I used a A100-80GB GPU on Runpod for the video!
See it live and in action πΊ
Startup π
- Clone this repo
git clone https://github.com/nicknochnack/Llama2RAG - Go into the directory
cd Llama2RAG - Startup jupyter by running
jupyter labin a terminal or command prompt - Update the
auth_tokenvariable in the notebook. - Hit
Ctrl + Enterto run through the notebook! - Go back to my YouTube channel and like and subscribe π...no seriously...please! lol
- If you want to start up the streamlit app run
streamlit run app.py(make sure you update your auth token in there as well!)
Other References π
-Llama 2 70b Chat Model Card:hugging face model card on the model used for the video.
-Llama Index Doco:sick library used for RAG.
Who, When, Why?
π¨πΎβπ» Author: Nick Renotte
π
Version: 1.x
π License: This project is licensed under the MIT license. Feel free to use it, just don't do bad things with it.