Image-Text-to-Text
shufanshen commited on
Commit
c432fc1
·
verified ·
1 Parent(s): 2351ff4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -1
README.md CHANGED
@@ -2,4 +2,15 @@
2
  license: cc-by-sa-4.0
3
  ---
4
 
5
- This repository is the pre-trained weights and metadata of [VL-SAE](https://github.com/ssfgunner/VL-SAE).
 
 
 
 
 
 
 
 
 
 
 
 
2
  license: cc-by-sa-4.0
3
  ---
4
 
5
+ This repository is the pre-trained weights and metadata of [VL-SAE](https://arxiv.org/abs/2510.21323), which helps users to understand the vision-language alignment of VLMs via concepts.
6
+
7
+ Source codes are available at [here](https://github.com/ssfgunner/VL-SAE).
8
+ ```bash
9
+ # Download using huggingface_cli
10
+ pip install huggingface_hub
11
+ huggingface-cli download shufanshen/VL-SAE
12
+
13
+ # Download using git
14
+ git lfs install
15
+ git clone git@hf.co:shufanshen/VL-SAE
16
+ ```