lm-sys / lm-sys/FastChat

ChatGLM-PTuning +Fastchat

Open
#1,165 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

ChatGLM-PTuning A fine-tuned model that cannot be deployed on fastchat. An error Some weights of ChatGLMForConditionalGeneration were not initialized from the model: the at /raid/users/lifei/ChatGLM-6B-Ptuning/chatglm and are newly initialized

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 deployment failure with the fine-tuned ChatGLM model at /raid/users/lifei/ChatGLM-6B-Ptuning/chatglm and inspect the reported weight-initialization error. Locate the FastChat model-loading entry point, then verify that the fine-tuned checkpoint deploys without newly initialized weights. No FastChat file or test is named, so the relevant entry point must first be identified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.