HuggingFace Deploy Instructions

This commit is contained in:
Raven Scott 2023-05-06 01:45:01 +02:00
parent d1807d37ad
commit 4ff16b4fc7

View File

@ -1,8 +1,8 @@
# How to Deploy on Hugging Face # How to Deploy on Hugging Face
1) Put all of the bots files within your HuggingFace Git Repo. 1) Move the "assets" directory and llamabot.js, package.json files into your HuggingFace repo directory.
2) Move the files Dockerfile - start.sh - startServices.json. (Overwrite the docker file found in the root of the project) 2) Move the files huggingface-config/Dockerfile - huggingface-config/start.sh - huggingface-config/startServices.json into the root of the hugging face repo.
3) Edit Docker file as you need, the dockerfile is set to automatically download Vicuna 1.1 7B 3) Edit Docker file as you need, the dockerfile is set to automatically download Vicuna 1.1 7B
@ -11,3 +11,7 @@
You should then see the bot being built and deployed on HuggingFace 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. pm2 log will run automatically so you can see frontend and backend logs.
`test on  main ls
assets Dockerfile llama.js package.json README.md startServices.json start.sh
`