This chatbot is created using the open-source Llama 2 LLM model from Meta.
Particularly, we're using the Llama2-7B model deployed by the Andreessen Horowitz (a16z) team and hosted on the Replicate platform.
This app was refactored from a16z's implementation of their LLaMA2 Chatbot to be light-weight for deployment to the Streamlit Community Cloud.
streamlit
replicate
To use this app, you'll need to get your own Replicate API token.
After signing up to Replicate, you can access your API token from this page.
As mentioned above, this chatbot implementation uses the Llama2-7B model that was trained on 7 billion parameters.
You can also try out the larger models: