Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fixbug for chatglm_v2's RetaryEmbedding dtype #9476

Conversation

mingMelody
Copy link
Contributor

PR types

Bug fixes

PR changes

Models

Description

chatglm_v2的RetaryEmbedding的实现与pytorch相比在dtype的使用上存在差别,从而导致两者在推理过程中可能出现精度误差,对其进行了修复

  • pytroch实现
截屏2024-11-21 19 37 01
  • paddle实现(修正后)
截屏2024-11-21 19 37 25

Copy link

paddle-bot bot commented Nov 21, 2024

Thanks for your contribution!

Copy link

codecov bot commented Nov 21, 2024

Codecov Report

Attention: Patch coverage is 80.00000% with 1 line in your changes missing coverage. Please review.

Project coverage is 53.08%. Comparing base (9ee691a) to head (cc27fff).
Report is 9 commits behind head on develop.

Files with missing lines Patch % Lines
paddlenlp/transformers/chatglm_v2/modeling.py 80.00% 1 Missing ⚠️
Additional details and impacted files
@@             Coverage Diff             @@
##           develop    #9476      +/-   ##
===========================================
- Coverage    53.40%   53.08%   -0.32%     
===========================================
  Files          685      685              
  Lines       110166   108843    -1323     
===========================================
- Hits         58837    57784    -1053     
+ Misses       51329    51059     -270     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.


🚨 Try these New Features:

@yuanlehome yuanlehome merged commit e3db4c0 into PaddlePaddle:develop Nov 25, 2024
10 of 12 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants