lm-sys / lm-sys/FastChat

使用gpt-3.5-turbo llm_api报错

Open
#2,301 3 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

2023-08-24 11:10:06 | ERROR | stderr | Process model_worker(27196):
2023-08-24 11:10:06 | ERROR | stderr | Traceback (most recent call last):
2023-08-24 11:10:06 | ERROR | stderr | File "D:\env\miniconda3\envs\langchain-ChatGLM\lib\multiprocessing\process.py", line 314, in _bootstrap
2023-08-24 11:10:06 | ERROR | stderr | self.run()
2023-08-24 11:10:06 | ERROR | stderr | File "D:\env\miniconda3\envs\langchain-ChatGLM\lib\multiprocessing\process.py", line 108, in run
2023-08-24 11:10:06 | ERROR | stderr | self._target(*self._args, **self._kwargs)
2023-08-24 11:10:06 | ERROR | stderr | File "D:\job\langchain-ChatGLM\server\llm_api.py", line 194, in run_model_worker
2023-08-24 11:10:06 | ERROR | stderr | app = create_model_worker_app(*args, **kwargs)
2023-08-24 11:10:06 | ERROR | stderr | File "D:\job\langchain-ChatGLM\server\llm_api.py", line 128, in create_model_worker_app
2023-08-24 11:10:06 | ERROR | stderr | worker = ModelWorker(
2023-08-24 11:10:06 | ERROR | stderr | File "D:\env\miniconda3\envs\langchain-ChatGLM\lib\site-packages\fastchat\serve\model_worker.py", line 196, in __init__
2023-08-24 11:10:06 | ERROR | stderr | super().__init__(
2023-08-24 11:10:06 | ERROR | stderr | File "D:\env\miniconda3\envs\langchain-ChatGLM\lib\site-packages\fastchat\serve\model_worker.py", line 84, in __init__
2023-08-24 11:10:06 | ERROR | stderr | self.conv.sep_style = int(self.conv.sep_style)
2023-08-24 11:10:06 | ERROR | stderr | TypeError: int() argument must be a string, a bytes-like object or a real number, not 'NoneType'

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 in server/llm_api.py at create_model_worker_app and run_model_worker, then follow the traceback into fastchat/serve/model_worker.py. Reproduce the gpt-3.5-turbo worker startup failure and determine why conv.sep_style is None; done means the worker starts without this TypeError and the relevant behavior is covered or explained.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, backend
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 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.