Hugging Face's logo

OpenGVLab
/
InternVL-14B-224px

Image Feature Extraction
Transformers
PyTorch
Safetensors
internvl
feature-extraction
custom_code
Model card Files Community
4
czczup commited on
Commit
d76eb45
•
1 Parent(s): c4036dd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -30,6 +30,16 @@ It is _**the largest open-source vision/vision-language foundation model (14B)**
30
  - Image size: 224 x 224
31
  - **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi
32
 
 
 
 
 
 
 
 
 
 
 
33
  ## Model Usage
34
 
35
  ```python
 
30
  - Image size: 224 x 224
31
  - **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi
32
 
33
+ ## Zero-Shot Performance
34
+
35
+ See this [document](https://github.com/OpenGVLab/InternVL/tree/main) for more details about the zero-shot evaluation.
36
+
37
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/KfsrXioPU77T48sRb60oL.png)
38
+
39
+
40
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/q5UkfrEix6w3mnn_1w4ja.png)
41
+
42
+
43
  ## Model Usage
44
 
45
  ```python