Hugging Face's logo

nvidia
/
NVIDIA-Nemotron-Nano-12B-v2-VL-BF16

Image-Text-to-Text
Transformers
Safetensors
nvidia
VLM
conversational
Model card Files
xet
Community
7
amalad commited on
Commit
c763641
·
1 Parent(s): fc94dd8

Update README

Browse files
Files changed (1) hide show
  1. README.md +15 -18
README.md CHANGED
@@ -722,24 +722,21 @@ Labeling Method by dataset: <br>
722
 
723
  Evaluation benchmarks scores: <br>
724
 
725
- <br>
726
- | Benchmarks | Score|
727
- |--------------------|--------------------------|
728
- | MMMU* | 68 |
729
- | MathVista* | 76.9 |
730
- | AI2D | 87.11 |
731
- | OCRBenchv2 | 62.0 |
732
- | OCRBench | 85.6 |
733
- | OCR-Reasoning | 36.4 |
734
- | ChartQA | 89.72 |
735
- | DocVQA | 94.39 |
736
- | Video-MME w/o sub | 65.9 |
737
- | Vision Average | 74.0 |
738
-
739
-
740
- <br>
741
-
742
- # Inference:
743
  **Acceleration Engine:** [vLLM] <br>
744
  **Acceleration Engine:** [TRT-LLM] <br>
745
 
 
722
 
723
  Evaluation benchmarks scores: <br>
724
 
725
+ | Benchmarks | Score |
726
+ |--------------------|-------|
727
+ | MMMU* | 68 |
728
+ | MathVista* | 76.9 |
729
+ | AI2D | 87.11 |
730
+ | OCRBenchv2 | 62.0 |
731
+ | OCRBench | 85.6 |
732
+ | OCR-Reasoning | 36.4 |
733
+ | ChartQA | 89.72 |
734
+ | DocVQA | 94.39 |
735
+ | Video-MME w/o sub | 65.9 |
736
+ | Vision Average | 74.0 |
737
+
738
+
739
+ # Inference: <br>
 
 
 
740
  **Acceleration Engine:** [vLLM] <br>
741
  **Acceleration Engine:** [TRT-LLM] <br>
742