.. | ||
Dockerfile | ||
README.md | ||
start.sh | ||
startServices.json |
How to Deploy on Hugging Face
-
Move the "assets" directory and llamabot.js, package.json files into your HuggingFace repo directory.
-
Move the files huggingface-config/Dockerfile - huggingface-config/start.sh - huggingface-config/startServices.json into the root of the hugging face repo.
-
Edit Docker file as you need, the dockerfile is set to automatically download Vicuna 1.1 7B
-
Move default.env into your repo as .env and edit for your needs
-
Push the changes
You should then see the bot being built and deployed on HuggingFace
pm2 log will run automatically so you can see frontend and backend logs.
PLEASE NOTE: Your hugging face repo should remain private!