Hugging Face's logo

nvidia
/
OpenReasoning-Nemotron-1.5B

Text Generation
Transformers
Safetensors
English
qwen2
nvidia
code
conversational
text-generation-inference
Model card Files Community
OpenReasoning-Nemotron-1.5B / README.md
smajumdar94's picture
smajumdar94
Update README.md
9833ada verified
preview code
|
raw
history blame
9.95 kB
metadata
license: cc-by-4.0
language:
  - en
base_model:
  - Qwen/Qwen2.5-1.5B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
  - nvidia
  - code

OpenReasoning-Nemotron-1.5B Overview

Description:

OpenReasoning-Nemotron-1.5B is a large language model (LLM) which is a derivative of Qwen2.5-1.5B-Instruct (AKA the reference model). It is a reasoning model that is post-trained for reasoning about math, code and science solution generation. The model supports a context length of 64K tokens. The OpenReasoning model is available in the following sizes: 1.5B, 7B and 14B and 32B.

This model is ready for commercial/non-commercial research use.

License/Terms of Use:

GOVERNING TERMS: Use of the models listed above are governed by the Creative Commons Attribution 4.0 International License (CC-BY-4.0). ADDITIONAL INFORMATION: Apache 2.0 License

Scores on Reasoning Benchmarks

Model AritificalAnalysisIndex GPQA MMLU-PRO HLE LiveCodeBench SciCode AIME24 AIME25 HMMT FEB 25 BRUMO25
1.5B - 31.6 47.5 5.5 28.6 2.2 55.5 45.6 31.5 50.6
7B 54.7 61.1 71.9 8.3 63.3 16.2 84.7 78.2 63.5 80.3
14B 60.9 71.6 77.5 10.1 67.8 23.5 87.8 82.0 71.2 87.7
32B 64.3 73.1 80.0 11.9 70.2 28.5 89.2 84.0 73.8 88.0

Scores for Math Reasoning Benchmarks with GenSelect

Model Pass@1 (Avg@64) Majority@64 GenSelect@64
1.5B
AIME24 55.5 76.7 76.7
AIME25 45.6 70.0 70.0
HMMT Feb 25 31.5 46.7 53.3
BRUNO25 50.6 70.0 73.3
7B
AIME24 84.7 93.3 93.3
AIME25 78.2 86.7 93.3
HMMT Feb 25 63.5 83.3 90.0
BRUNO25 80.3 93.3 96.7
14B
AIME24 87.8 93.3 93.3
AIME25 82.0 90.0 90.0
HMMT Feb 25 71.2 86.7 93.3
BRUNO25 87.7 96.7 96.7
32B
AIME24 89.2 93.3 93.3
AIME25 84.0 90.0 93.3
HMMT Feb 25 73.8 86.7 96.7
BRUNO25 88.0 96.7 100.0

How to use the models?

To run inference on coding problems:

import transformers
import torch
model_id = "nvidia/OpenReasoning-Nemotron-1.5B"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

# Code generation prompt
prompt = """You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.
Please use python programming language only.
You must use ```python for just the final solution code block with the following format:
```python
# Your code here
```
{user}
"""

messages = [
    {
        "role": "user",
        "content": prompt.format(user="Write a program to calculate the sum of the first $N$ fibonacci numbers")},
]
outputs = pipeline(
    messages,
    max_new_tokens=64000,
)
print(outputs[0]["generated_text"][-1]['content'])

Citation

If you find the data useful, please cite:

@article{ahmad2025opencodereasoning,
      title={OpenCodeReasoning: Advancing Data Distillation for Competitive Coding}, 
      author={Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, Aleksander Ficek, Siddhartha Jain, Jocelyn Huang, Vahid Noroozi, Boris Ginsburg},
      year={2025},
      eprint={2504.01943},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2504.01943}, 
}

@misc{ahmad2025opencodereasoningiisimpletesttime,
      title={OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique}, 
      author={Wasi Uddin Ahmad and Somshubra Majumdar and Aleksander Ficek and Sean Narenthiran and Mehrzad Samadi and Jocelyn Huang and Siddhartha Jain and Vahid Noroozi and Boris Ginsburg},
      year={2025},
      eprint={2507.09075},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2507.09075}, 
}

@misc{moshkov2025aimo2winningsolutionbuilding,
      title={AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset}, 
      author={Ivan Moshkov and Darragh Hanley and Ivan Sorokin and Shubham Toshniwal and Christof Henkel and Benedikt Schifferer and Wei Du and Igor Gitman},
      year={2025},
      eprint={2504.16891},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2504.16891}, 
}

Additional Information:

Deployment Geography:

Global

Use Case:

This model is intended for developers and researchers who work on competitive math, code and science problems. It has been trained via only supervised fine-tuning to achieve strong scores on benchmarks.

Release Date:

Huggingface [07/16/2025] via https://huggingface.co/nvidia/OpenReasoning-Nemotron-1.5B/

Reference(s):

[2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding [2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding [2504.16891] AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset

Model Architecture:

Architecture Type: Dense decoder-only Transformer model Network Architecture: Qwen-1.5B-Instruct
**This model was developed based on Qwen2.5-1.5B-Instruct and has 1.5B model parameters.

OpenReasoning-Nemotron-1.5B was developed based on Qwen2.5-1.5B-Instruct and has 1.5B model parameters.

OpenReasoning-Nemotron-7B was developed based on Qwen2.5-7B-Instruct and has 7B model parameters.

OpenReasoning-Nemotron-14B was developed based on Qwen2.5-14B-Instruct and has 14B model parameters.

OpenReasoning-Nemotron-32B was developed based on Qwen2.5-32B-Instruct and has 32B 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 64,000 tokens

Output:

Output Type(s): Text
Output Format: String
Output Parameters: One-Dimensional (1D)
Other Properties Related to Output: Context length up to 64,000 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.

Software Integration :

  • Runtime Engine: NeMo 2.3.0
  • Recommended Hardware Microarchitecture Compatibility:
    NVIDIA Ampere
    NVIDIA Hopper
  • Preferred/Supported Operating System(s): Linux

Model Version(s):

1.0 (7/16/2025)
OpenReasoning-Nemotron-32B
OpenReasoning-Nemotron-14B
OpenReasoning-Nemotron-7B
OpenReasoning-Nemotron-1.5B

Training and Evaluation Datasets:

Training Dataset:

The training corpus for OpenReasoning-Nemotron-1.5B is comprised of questions from OpenCodeReasoning dataset, OpenCodeReasoning-II, OpenMathReasoning, and the Synthetic Science questions from the Llama-Nemotron-Post-Training-Dataset. All responses are generated using DeepSeek-R1-0528. We also include the instruction following and tool calling data from Llama-Nemotron-Post-Training-Dataset without modification.

Data Collection Method: Hybrid: Automated, Human, Synthetic
Labeling Method: Hybrid: Automated, Human, Synthetic
Properties: 5M DeepSeek-R1-0528 generated responses from OpenCodeReasoning questions (https://huggingface.co/datasets/nvidia/OpenCodeReasoning), OpenMathReasoning, and the Synthetic Science questions from the Llama-Nemotron-Post-Training-Dataset. We also include the instruction following and tool calling data from Llama-Nemotron-Post-Training-Dataset without modification.

Evaluation Dataset:

We used the following benchmarks to evaluate the model holistically.

Math

  • AIME 2024/2025
  • HMMT
  • BRUNO 2025

Code

  • LiveCodeBench
  • SciCode

Science

  • GPQA
  • MMLU-PRO
  • HLE

Data Collection Method: Hybrid: Automated, Human, Synthetic
Labeling Method: Hybrid: Automated, Human, Synthetic

Inference:

Acceleration Engine: vLLM, Tensor(RT)-LLM
Test Hardware NVIDIA H100-80GB

Ethical Considerations:

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.

For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.