567-labs / fastllm

A collection of LLM services you can self host via docker or modal labs to support your applications development
MIT License
181 stars 23 forks source link

Updated the article with a walkthrough on how to use Modal #30

Closed ivanleomk closed 9 months ago

ivanleomk commented 9 months ago

I've rewritten the original section that I wrote on the code walkthrough. This should be a lot more high-level with inspiration taken from this article ( https://modal.com/docs/examples/tgi_mixtral ) that they recently published.

I wasn't able to refactor the custom image to use a volume so I've kept the run_function instead since it seems to be a much simpler implementation