riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 18:22:34 +06:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

[ClipVision] accelerate support for clip-vision (#27851)

Browse Source 
support accelerate for clip-vision
This commit is contained in:
Younes Belkada 2023-12-05 14:04:20 +01:00 committed by GitHub
parent b7e6d120c1
commit 3e68944cc4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/transformers/models/clip/modeling_clip.py
View File

@ -870,6 +870,7 @@ class CLIPVisionTransformer(nn.Module):
class CLIPVisionModel(CLIPPreTrainedModel):
config_class = CLIPVisionConfig
main_input_name = "pixel_values"
_no_split_modules = ["CLIPEncoderLayer"]
def __init__(self, config: CLIPVisionConfig):
super().__init__(config)