Skip to content

Conversation

@wj-Mcat
Copy link
Contributor

@wj-Mcat wj-Mcat commented Jan 31, 2023

PR types

New features

PR changes

Models

Description

在AutoModel中支持ChineseCLIP 模型

测试代码:

from paddlenlp.transformers import AutoModel
model = AutoModel.from_pretrained("OFA-Sys/chinese-clip-vit-huge-patch14")

@paddle-bot
Copy link

paddle-bot bot commented Jan 31, 2023

Thanks for your contribution!

@wj-Mcat wj-Mcat marked this pull request as ready for review January 31, 2023 05:16
@wj-Mcat wj-Mcat changed the title [New features] support chineseclip model [New features] support chineseclip auto model Jan 31, 2023
@wj-Mcat wj-Mcat requested a review from sijunhe January 31, 2023 05:17
@codecov
Copy link

codecov bot commented Jan 31, 2023

Codecov Report

Merging #4585 (5dedc67) into develop (29bf84c) will increase coverage by 0.13%.
The diff coverage is n/a.

@@             Coverage Diff             @@
##           develop    #4585      +/-   ##
===========================================
+ Coverage    41.76%   41.89%   +0.13%     
===========================================
  Files          434      434              
  Lines        61872    61872              
===========================================
+ Hits         25838    25922      +84     
+ Misses       36034    35950      -84     
Impacted Files Coverage Δ
paddlenlp/transformers/auto/modeling.py 76.30% <ø> (ø)
paddlenlp/transformers/ernie_layout/tokenizer.py 72.72% <ø> (+50.90%) ⬆️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

Copy link
Contributor

@sijunhe sijunhe left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

@wj-Mcat wj-Mcat merged commit 3f419c4 into PaddlePaddle:develop Jan 31, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants