This is a chatbot app built using the Llama 2 open-source LLM model from Meta. It uses 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.
You can try the bot here - [LLAMA2 Chatbot] https://llama2app-dq6xbwry2tf2cw7mnrhsem.streamlit.app/
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 their website. You can also try out other Llama 2 models, such as Llama2-13B and Llama2-70B. For more information, please refer to this Streamlit blog post.
- Clone this repository
git clone https://github.com/wolfsbane9513/Llama2_streamlit.git
- Install dependencies
pip install -r requirements.txt
- Run the app
streamlit run app.py
Enter your Replicate API token and a message prompt in the chat box to start chatting with the Llama 2 chatbot.
This project is licensed under the MIT License - see the LICENSE file for details.