Splend1dchan
/

ViT-H-14-laion2B-s32B-b79K

Zero-Shot Image Classification

Inference Endpoints

Model card Files Files and versions Community

Splend1dchan commited on Apr 16, 2023

Commit

dc1b0b4

·

1 Parent(s): 5f5d351

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 # This model weight is identical to laion/CLIP-ViT-H-14-laion2B-s32B-b79K, but with the pytorch_model component only (without open_clip_pytorch_model.bin).
-This is to support loading the model as a ClipModel. As a failed to load the original model using AutoModel (feedback appreciated)
 With this distribution, I was finally able to load from AutoModel, and further support image classification tasks using my self-defined class CLIPViTForImageClassification listed below.
 However, there is still a small issue that I cannot resolve, I can only load the model if I git clone this repo to local, if I load from web, the loading still fails.
 ```python

 # This model weight is identical to laion/CLIP-ViT-H-14-laion2B-s32B-b79K, but with the pytorch_model component only (without open_clip_pytorch_model.bin).
+This is to support loading the model as a ClipModel, as I failed to load the original model using AutoModel (feedback appreciated)
 With this distribution, I was finally able to load from AutoModel, and further support image classification tasks using my self-defined class CLIPViTForImageClassification listed below.
 However, there is still a small issue that I cannot resolve, I can only load the model if I git clone this repo to local, if I load from web, the loading still fails.
 ```python