SiyouLi commited on
Commit
920c782
·
verified ·
1 Parent(s): 082fef0

Add files using upload-large-folder tool

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -14,6 +14,7 @@ tags:
14
  ## What’s different vs standard CLIP
15
  - based on CLIP ViT-B/32 (from [laion/CLIP-ViT-B-32-laion2B-s34B-b79K](https://huggingface.co/laion/CLIP-ViT-B-32-laion2B-s34B-b79K))
16
  - **Longer text context**: `max_position_embeddings=512` (vs the usual 77).
 
17
  ## Usage
18
 
19
  ```python
@@ -43,9 +44,6 @@ with torch.no_grad():
43
  print(probs[0].tolist())
44
  ```
45
 
46
- ## Training data
47
- - Train data: 1.67M image-caption pairs, caption regenerated by Qwen2.5-VL-72B (512-token max length), images sampled from LAION-2B.
48
-
49
  ## Zero-shot classification example
50
 
51
  ```python
 
14
  ## What’s different vs standard CLIP
15
  - based on CLIP ViT-B/32 (from [laion/CLIP-ViT-B-32-laion2B-s34B-b79K](https://huggingface.co/laion/CLIP-ViT-B-32-laion2B-s34B-b79K))
16
  - **Longer text context**: `max_position_embeddings=512` (vs the usual 77).
17
+ - Train data: 1.67M image-caption pairs, caption regenerated by Qwen2.5-VL-72B (512-token max length), images sampled from LAION-2B.
18
  ## Usage
19
 
20
  ```python
 
44
  print(probs[0].tolist())
45
  ```
46
 
 
 
 
47
  ## Zero-shot classification example
48
 
49
  ```python