Hugging Face's logo

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

Zero-Shot Image Classification
Safetensors
prolip
pytorch_model_hub_mixin
model_hub_mixin
Model card Files
xet
Community
1
SanghyukChun commited on
Commit
5c872ad
·
verified ·
1 Parent(s): d45295a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -10,7 +10,9 @@ base_model:
10
  ---
11
  ## Official implementation of fine-tuned ViT-H/14 ProLIP on DataComp 1B
12
 
13
- - This weight is a fine-tuned version of ViT-H/14 provided by https://huggingface.co/apple/DFN5B-CLIP-ViT-H-14
 
 
14
  - Fine-tuned dataset
15
  - DataComp 1B / Seen samples 1.28B
16
  - Architectural difference
 
10
  ---
11
  ## Official implementation of fine-tuned ViT-H/14 ProLIP on DataComp 1B
12
 
13
+ - This weight is a fine-tuned version of ViT-H/14 by Probabilistic Language-Image Pre-Training (ProLIP)
14
+ - Pre-trained weight
15
+ - https://huggingface.co/apple/DFN5B-CLIP-ViT-H-14
16
  - Fine-tuned dataset
17
  - DataComp 1B / Seen samples 1.28B
18
  - Architectural difference