Hugging Face's logo

AIDC-AI
/
Ovis2-4B

Image-Text-to-Text
Transformers
Safetensors
English
Chinese
ovis
text-generation
MLLM
conversational
custom_code
Model card Files Community
1
liyang commited on
Commit
d2062de
·
verified ·
1 Parent(s): 94a5eff

updata Benchmark and Image in README

Browse files
Files changed (1) hide show
  1. README.md +22 -13
README.md CHANGED
@@ -47,19 +47,28 @@ We are pleased to announce the release of **Ovis2**, our latest advancement in m
47
  | Ovis2-34B | aimv2-1B-patch14-448 | Qwen2.5-32B-Instruct | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2-34B) | - |
48
 
49
  ## Performance
50
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/637aebed7ce76c3b834cea37/aCuSemmHy_MhrDaBiYfco.png)
51
-
52
- |Benchmark|Ovis2-1B|Ovis2-2B|Ovis2-4B|Ovis2-8B|Ovis2-16B|Ovis2-34B|
53
- |:---:|:---:|:---:|:---:|:---:|:---:|:---:|
54
- |MMBench-V1.1<sub>test</sub>|68.5|77.2|81.4|83.3|85.2|86.2|
55
- |MMStar|52.0|59.0|61.7|64.4|66.9|69.4|
56
- |MMMU<sub>val</sub>|36.0|45.3|48.0|59.0|59.6|65.6|
57
- |MathVista<sub>testmini</sub>|59.5|64.4|69.1|71.4|74.9|77.0|
58
- |HallBench<sub>avg</sub>|44.5|50.2|54.0|56.0|55.9|58.8|
59
- |AI2D<sub>test</sub>|76.8|82.6|85.5|86.8|86.1|88.4|
60
- |OCRBench|88.7|87.5|91.0|89.3|88.2|89.8|
61
- |MMVet|50.3|58.6|65.5|68.5|68.4|75.5|
62
- |Average|59.5|65.6|69.5|72.3|73.1|76.3|
 
 
 
 
 
 
 
 
 
63
 
64
  ## Usage
65
  Below is a code snippet demonstrating how to run Ovis with various input types. For additional usage instructions, including inference wrapper and Gradio UI, please refer to [Ovis GitHub](https://github.com/AIDC-AI/Ovis?tab=readme-ov-file#inference).
 
47
  | Ovis2-34B | aimv2-1B-patch14-448 | Qwen2.5-32B-Instruct | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2-34B) | - |
48
 
49
  ## Performance
50
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6076587d310e510df1db14bc/X1Ccbj48Icun1vATqvE3Z.png)
51
+
52
+ ### Image Benchmark
53
+ | Benchmark | Qwen2.5-VL-7B | InternVL2.5-8B-MPO | MiniCPM-o-2.6 | Ovis1.6-9B | InternVL2.5-4B-MPO | Ovis2-4B | Ovis2-8B |
54
+ |:-----------------------------|:---------------:|:--------------------:|:---------------:|:------------:|:--------------------:|:----------:|:----------:|
55
+ | MMBench-V1.1<sub>test</sub> | 82.6 | 82.0 | 80.6 | 80.5 | 77.8 | 81.4 | **83.6** |
56
+ | MMStar | 64.1 | **65.2** | 63.3 | 62.9 | 61 | 61.9 | 64.6 |
57
+ | MMMU<sub>val</sub> | 56.2 | 54.8 | 50.9 | 55 | 51.8 | 49.0 | **57.4** |
58
+ | MathVista<sub>testmini</sub> | 65.8 | 67.9 | **73.3** | 67.3 | 64.1 | 69.6 | 71.8 |
59
+ | HallusionBench | **56.3** | 51.7 | 51.1 | 52.2 | 47.5 | 53.8 | **56.3** |
60
+ | AI2D | 84.1 | 84.5 | 86.1 | 84.4 | 81.5 | 85.7 | **86.6** |
61
+ | OCRBench | 87.7 | 88.2 | 88.9 | 83 | 87.9 | **91.1** | 89.1 |
62
+ | MMVet | 66.6 | **68.1** | 67.2 | 65 | 66 | 65.5 | 65.1 |
63
+ | MMBench<sub>test</sub> | 83.4 | 83.2 | 83.2 | 82.7 | 79.6 | 83.2 | **84.9** |
64
+ | MMT-Bench<sub>val</sub> | 62.7 | 62.5 | 62.3 | 64.9 | 61.6 | 65.2 | **66.6** |
65
+ | RealWorldQA | 68.8 | 71.1 | 68.0 | 70.7 | 64.4 | 71.1 | **72.5** |
66
+ | BLINK | 56.1 | **56.6** | 53.9 | 48.5 | 50.6 | 53.0 | 54.3 |
67
+ | QBench | 77.9 | 73.8 | 78.7 | 76.7 | 71.5 | 78.1 | **78.9** |
68
+ | ABench | 75.6 | 77.0 | **77.5** | 74.4 | 75.9 | **77.5** | 76.4 |
69
+ | MTVQA | 28.5 | 27.2 | 23.1 | 19.2 | 28 | 29.4 | **29.7** |
70
+
71
+ ### Video Benchmark
72
 
73
  ## Usage
74
  Below is a code snippet demonstrating how to run Ovis with various input types. For additional usage instructions, including inference wrapper and Gradio UI, please refer to [Ovis GitHub](https://github.com/AIDC-AI/Ovis?tab=readme-ov-file#inference).