OpenMath-Nemotron-32B is created by finetuning Qwen/Qwen2.5-32B on OpenMathReasoning dataset.
This model is ready for commercial use.
Evaluation Results
OpenMath-Nemotron models achieve state-of-the-art results on popular mathematical benchmarks. We present metrics as pass@1 (maj@64) where pass@1
is an average accuracy across 64 generations and maj@64 is the result of majority voting.
Please see our paper for more details on the evaluation setup.
We provide all instructions
to fully reproduce our results, including data generation.
How to use the models?
Our models can be used in 3 inference modes: chain-of-thought (CoT), tool-integrated reasoning (TIR) and generative solution selection (GenSelect).
To run inference with CoT mode, you can use this example code snippet.
python
1import transformers
2import torch
34model_id ="nvidia/OpenMath-Nemotron-32B"56pipeline = transformers.pipeline(7"text-generation",8 model=model_id,9 model_kwargs={"torch_dtype": torch.bfloat16},10 device_map="auto",11)1213messages =[14{15"role":"user",16"content":"Solve the following math problem. Make sure to put the answer (and only answer) inside \\boxed{}.\n\n"+17"What is the minimum value of $a^2+6a-7$?"},18]1920outputs = pipeline(21 messages,22 max_new_tokens=4096,23)24print(outputs[0]["generated_text"][-1]['content'])
Please note that these models have not been instruction tuned on general data and thus might not provide good answers outside of math domain.
Citation
If you find our work useful, please consider citing us!
bibtex
1@article{moshkov2025aimo2,
2 title = {AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset},
3 author = {Ivan Moshkov and Darragh Hanley and Ivan Sorokin and Shubham Toshniwal and Christof Henkel and Benedikt Schifferer and Wei Du and Igor Gitman},
4 year = {2025},
5 journal = {arXiv preprint arXiv:2504.16891}
6}
This model is intended to facilitate research in the area of mathematical reasoning.
Release Date:
Huggingface 04/23/2025
Model Architecture:
Architecture Type: Transformer decoder-only language model
Network Architecture: Qwen2.5
**This model was developed based on Qwen2.5-1.5B
** This model has 1.5B of model parameters.
Input:
Input Type(s): Text
Input Format(s): String
Input Parameters: One-Dimensional (1D)
Other Properties Related to Input: Context length up to 131,072 tokens
Output:
Output Type(s): Text
Output Format: String
Output Parameters: One-Dimensional (1D)
Other Properties Related to Output: Context length up to 131,072 tokens
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
