Update README.md
Browse files
README.md
CHANGED
@@ -114,6 +114,17 @@ outputs = pipeline(
|
|
114 |
print(outputs[0]["generated_text"][-1]['content'])
|
115 |
````
|
116 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
## Citation
|
118 |
|
119 |
If you find the data useful, please cite:
|
|
|
114 |
print(outputs[0]["generated_text"][-1]['content'])
|
115 |
````
|
116 |
|
117 |
+
To use the model with GenSelect inference, we recommend following our
|
118 |
+
[reference implementation in NeMo-Skills](https://github.com/NVIDIA/NeMo-Skills/blob/main/nemo_skills/pipeline/genselect.py).
|
119 |
+
Alternatively, you can manually extract the summary from all solutions and use this
|
120 |
+
[prompt](https://github.com/NVIDIA/NeMo-Skills/blob/main/nemo_skills/prompt/config/openmath/genselect.yaml) for the math problems.
|
121 |
+
We will add the prompt we used for the coding problems and a reference implementation soon!
|
122 |
+
|
123 |
+
You can learn more about GenSelect in these papers:
|
124 |
+
* [AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset](https://arxiv.org/abs/2504.16891)
|
125 |
+
* [GenSelect: A Generative Approach to Best-of-N](https://openreview.net/forum?id=8LhnmNmUDb)
|
126 |
+
|
127 |
+
|
128 |
## Citation
|
129 |
|
130 |
If you find the data useful, please cite:
|