Update README.md
Browse files
README.md
CHANGED
|
@@ -41,6 +41,10 @@ Starting from [NVIDIA-Nemotron-3-Nano-30B-A3B-BF16](https://huggingface.co/nvidi
|
|
| 41 |
|
| 42 |
To evaluate the outcome we use [Gemini 3 Flash](https://deepmind.google/models/gemini/flash/) as a VLM judge. Our final model achieves a +48% improvement over the Nano baseline.
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
---
|
| 45 |
## QuickStart
|
| 46 |
|
|
|
|
| 41 |
|
| 42 |
To evaluate the outcome we use [Gemini 3 Flash](https://deepmind.google/models/gemini/flash/) as a VLM judge. Our final model achieves a +48% improvement over the Nano baseline.
|
| 43 |
|
| 44 |
+
<p align="center">
|
| 45 |
+
<img src="overall_bar.png" alt="Evaluation Result" width="100%">
|
| 46 |
+
</p>
|
| 47 |
+
|
| 48 |
---
|
| 49 |
## QuickStart
|
| 50 |
|