UCSC-VLAA
/

ViT-L-14-CLIPS-Recap-DataComp-1B

Model card Files Files and versions

Yanqing0327 commited on Dec 17, 2024

Commit

e91dac9

·

verified ·

1 Parent(s): ea98b8e

Update README.md

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -15,9 +15,7 @@ datasets:
 ## Model Usage
 ### With OpenCLIP
-#### Note:
-#### 1. We made modifications to the tokenizer implementation in open_clip/tokenizer.py.
-#### 2. Due to differences in the default epsilon values for LayerNorm initialization between JAX and PyTorch, we adjusted the default epsilon value in open_clip/transformer.py to align the model's behavior.
 #### For more details, refer to https://github.com/UCSC-VLAA/CLIPS.
 ```

 ## Model Usage
 ### With OpenCLIP
+#### Note: We made modifications to the tokenizer implementation in open_clip/tokenizer.py.
 #### For more details, refer to https://github.com/UCSC-VLAA/CLIPS.
 ```