lm-sys / lm-sys/FastChat

failed to run FastChat with stable lm-zephyr-3b

Open
#3,000 0 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

nohup python -m fastchat.serve.controller --host 0.0.0.0 &
nohup python -m fastchat.serve.model_worker --model-path /Volumes/256/stablelm-zephyr-3b --host 0.0.0.0 --device mps &
sleep 40
nohup python -m fastchat.serve.gradio_web_server --host 0.0.0.0 &


Start fast chat without any issue.

But we use webui, I got the following error:

NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.

(Attention mask should be of size (1, 1, 1, 210), but is torch.Size([1, 1, 1, 1]))

(error_code: 50001)

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

Reproduce the failure using the listed controller, model_worker, and gradio_web_server commands with the stablelm-zephyr-3b model on MPS. Start at the web UI request path and the reported attention-mask error; done means the model can generate through the web UI without the 50001 error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, backend
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.