lm-sys / lm-sys/FastChat

custom model path local when load the open source model from huggingface

Open
#2,343 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

I using fastchat.serve.model_worker ModelWorker to create a worker, but when I read the source code this project, I can't find anywhere to use the parameters cache_dir in AutoXXX.from_pretrained(), so this
project only load the open sources model to the loacl dir "/.cache"? or do I have any approach for customizing the save path when loading the model(especially the model is over 8G almost)

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with fastchat.serve.model_worker.ModelWorker and inspect the AutoXXX.from_pretrained() calls mentioned in the issue. Check how model-loading options are passed and whether cache_dir can be exposed for a custom local path. Done means the supported loading path is documented or configurable and works for a large model.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
ai
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.