hiyouga / hiyouga/FastEdit

编辑完的baichuan-13b该如何保存

Open
#11 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.4k
Forks
103
PR merge metrics
No merged PRs in 30d

Description

我save_pretrained()后的模型推理时有nan错误

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the reported flow: edit the Baichuan-13B model, call save_pretrained(), reload it, and run inference. The issue names no files or tests, so trace the save and reload entry points used by the repository. Done means the saved model reloads and inference no longer produces NaN values.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
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.