lm-sys / lm-sys/FastChat

Get irrelevant answers when use fastchat.serve.cli on MacOS mps

Open
#637 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

When I use this command I get

python3 -m fastchat.serve.cli --model-path vicuna-7b --device mps --load-8bit
image

I used RTX3080 and could already work under CUDA by replacing special_tokens_map.json and tokenizer_config.json with v0 files, but using MPS on macOS would say something irrelevant
Can anyone solve this problem????

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 by reproducing the command through fastchat.serve.cli with --device mps and --load-8bit, then compare its output with the reported CUDA setup and the referenced tokenizer configuration files. Done means the cause of irrelevant responses on macOS MPS is identified and the command produces relevant answers, with the behavior checked against the issue's example.

Written by the indexing model from the issue text.

Assessment

Tech stack
macos, python
Domain
ai, desktop
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.