Hugging Face's logo

Kun-Xiang
/
AtomThink-EMOVA-8B

Safetensors
llava_llama
Model card Files
xet
 Community
1
Kun Xiang commited on
Commit
dbe7b49
·
verified ·
1 Parent(s): 7d560f5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -11,7 +11,6 @@ license: apache-2.0
11
  The model is post-trained based on EMOVA-8B and the AtomThink framework, and can be used to solve complex multimodal mathematical problems.
12
 
13
  # Comparison of accuracy with state-of-the-art methods on MathVista and MathVerse:
14
-
15
  | **Model** | **Inference** | **General** | **Math** | **Total** | **TL** | **TD** | **VI** | **VD** | **VO** | **Total** |
16
  |-----------------------|---------------|-------------|----------|-----------|----------|----------|----------|----------|----------|-----------|
17
  | Random Choice | - | - | - | 17.9 | 12.4 | 12.4 | 12.4 | 12.4 | 12.4 | 12.4 |
 
11
  The model is post-trained based on EMOVA-8B and the AtomThink framework, and can be used to solve complex multimodal mathematical problems.
12
 
13
  # Comparison of accuracy with state-of-the-art methods on MathVista and MathVerse:
 
14
  | **Model** | **Inference** | **General** | **Math** | **Total** | **TL** | **TD** | **VI** | **VD** | **VO** | **Total** |
15
  |-----------------------|---------------|-------------|----------|-----------|----------|----------|----------|----------|----------|-----------|
16
  | Random Choice | - | - | - | 17.9 | 12.4 | 12.4 | 12.4 | 12.4 | 12.4 | 12.4 |