Hugging Face's logo

ibm-granite
/
granite-vision-3.2-2b

Image-Text-to-Text
Transformers
Safetensors
English
llava_next
conversational
text-generation-inference
Model card Files Community
8
dhirajjoshi116 commited on
Commit
46525fb
·
verified ·
1 Parent(s): 792db68

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -26,7 +26,7 @@ We evaluated Granite Vision 3.2 alongside other vision-language models (VLMs) in
26
  | InfoVQA | 0.44 | 0.58 | 0.55 | 0.61 | **0.64** |
27
  | OCRBench | 0.65 | 0.75 | 0.64 | 0.64 | **0.77** |
28
  | LiveXiv VQA | 0.47 | 0.51 | **0.61** | - | **0.61** |
29
- | LiveXiv TQA | 0.36 | 0.38 | 0.48 | - | **0.55** |
30
  | **Other benchmarks** |
31
  | MMMU | 0.32 | 0.35 | 0.42 | **0.44** | 0.37 |
32
  | VQAv2 | 0.57 | 0.75 | 0.76 | 0.77 | **0.78** |
 
26
  | InfoVQA | 0.44 | 0.58 | 0.55 | 0.61 | **0.64** |
27
  | OCRBench | 0.65 | 0.75 | 0.64 | 0.64 | **0.77** |
28
  | LiveXiv VQA | 0.47 | 0.51 | **0.61** | - | **0.61** |
29
+ | LiveXiv TQA | 0.36 | 0.38 | 0.48 | - | **0.57** |
30
  | **Other benchmarks** |
31
  | MMMU | 0.32 | 0.35 | 0.42 | **0.44** | 0.37 |
32
  | VQAv2 | 0.57 | 0.75 | 0.76 | 0.77 | **0.78** |