SanghyukChun
/

ProLIP-ViT-H-14-FT-DC-1B-1_28B

pytorch_model_hub_mixin

model_hub_mixin

Model card Files Files and versions Community

SanghyukChun commited on 18 days ago

Commit

5c872ad

•

1 Parent(s): d45295a

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -10,7 +10,9 @@ base_model:
 ---
 ## Official implementation of fine-tuned ViT-H/14 ProLIP on DataComp 1B
-- This weight is a fine-tuned version of ViT-H/14 provided by https://huggingface.co/apple/DFN5B-CLIP-ViT-H-14
 - Fine-tuned dataset
     - DataComp 1B / Seen samples 1.28B
 - Architectural difference

 ---
 ## Official implementation of fine-tuned ViT-H/14 ProLIP on DataComp 1B
+- This weight is a fine-tuned version of ViT-H/14 by Probabilistic Language-Image Pre-Training (ProLIP)
+- Pre-trained weight
+    - https://huggingface.co/apple/DFN5B-CLIP-ViT-H-14
 - Fine-tuned dataset
     - DataComp 1B / Seen samples 1.28B
 - Architectural difference