metadata

library_name: transformers
license: other
license_name: nvidia-internal-scientific-research-and-development-model-license
license_link: >-
  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-internal-scientific-research-and-development-model-license/
pipeline_tag: text-generation
tags:
  - nvidia
  - pytorch

OpenCodeReasoning-Nemotron-14B Overview

Description

OpenCodeReasoning-Nemotron-14B is a large language model (LLM) which is a derivative of Qwen2.5-14B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning while code generation. The model supports a context length of 32K tokens.

This model is ready for commercial use.

License/Terms of Use

GOVERNING TERMS: Your use of this model is governed by the NVIDIA Internal Scientific Research and Development Model License.

Deployment Geography:

Global

Use Case:

This model is intended for developers and researchers building LLMs.

Release Date:

Huggingface [04/25/2025] via https://huggingface.co/nvidia/OpenCodeReasoning-Nemotron-14B/

References

[2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding

Model Architecture

Architecture Type: Dense decoder-only Transformer model
Network Architecture: Qwen2.5-14B-Instruct

Input

Input Type(s): Text
Input Format(s): String
Input Parameters: One-Dimensional (1D)
Other Properties Related to Input: Context length up to 32,768 tokens

Output

Output Type(s): Text
Output Format: String
Output Parameters: One-Dimensional (1D)
Other Properties Related to Output: Context length up to 32,768 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: Transformers, vLLM
Recommended Hardware Microarchitecture Compatibility:
- NVIDIA Ampere
- NVIDIA Hopper
Preferred/Supported Operating System(s): Linux

Model Version(s)

1.0 (4/25/2025)

Training Dataset

The training corpus for OpenCodeReasoning-Nemotron-14B is OpenCodeReasoning dataset, which is composed of competitive programming questions and DeepSeek-R1 generated responses.

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

Evaluation Dataset

We used the datasets listed in the next section to evaluate OpenCodeReasoning-Nemotron-14B.

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

LiveCodeBench

Easy	Medium	Hard	Avg.
97.6	74.4	27.6	59.4

CodeContests

Public	Private	Generated	All
57.1	34.5	40.2	23.6

Inference

Engine: vLLM
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 security vulnerabilities or NVIDIA AI Concerns here.

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}, 
}