Update README.md
Browse files
README.md
CHANGED
|
@@ -78,6 +78,11 @@ We evaluated our model in **Reasoning-On** mode across all benchmarks, except RU
|
|
| 78 |
All evaluations were done using [NeMo-Skills](https://github.com/NVIDIA/NeMo-Skills).
|
| 79 |
We published a [tutorial](https://nvidia.github.io/NeMo-Skills/tutorials/2025/08/22/reproducing-nvidia-nemotron-nano-9b-v2-evals/) with all details necessary to reproduce our evaluation results.
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
|
| 82 |
## Model Architecture
|
| 83 |
|
|
|
|
| 78 |
All evaluations were done using [NeMo-Skills](https://github.com/NVIDIA/NeMo-Skills).
|
| 79 |
We published a [tutorial](https://nvidia.github.io/NeMo-Skills/tutorials/2025/08/22/reproducing-nvidia-nemotron-nano-9b-v2-evals/) with all details necessary to reproduce our evaluation results.
|
| 80 |
|
| 81 |
+
## Reasoning Budget Control
|
| 82 |
+
|
| 83 |
+
This model supports runtime “thinking” budget control. During inference, the user can specify how many tokens the model is allowed to "think".
|
| 84 |
+
|
| 85 |
+
|
| 86 |
|
| 87 |
## Model Architecture
|
| 88 |
|