Nemotron-Post-Training-v3
Collection
Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 52 items • Updated • 150
messages listlengths 9 353 | uuid stringlengths 36 36 | license stringclasses 1
value |
|---|---|---|
[
{
"role": "system",
"content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n\n<ROLE>\nYour primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and priorit... | 2150a3fd-8078-4b75-83f0-12165cd738e1 | cc-by-4.0 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | 67ae7ef5-cb15-4ffd-a9b1-a80cc4c1435c | cc-by-4.0 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | ba0fc47c-c13e-400e-9068-3a60982f7fa0 | cc-by-4.0 |
[{"role":"system","content":"You are opencode, an interactive CLI tool that helps users with softwar(...TRUNCATED) | 9bf18aef-fb6c-4b61-be9f-0a91af1b716a | cc-by-4.0 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | e9743acb-1a39-4114-abad-987fbdd032b2 | cc-by-4.0 |
[{"role":"system","content":"You are an AI agent that helps solve software engineering tasks. You fo(...TRUNCATED) | 1c10888e-6911-4ec0-adf7-76c1643b505b | cc-by-4.0 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | f5d3f841-d10c-4950-b1ba-a47e6c87575f | cc-by-4.0 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | 4c322952-ca74-4922-aada-20e5a69c747c | cc-by-4.0 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | 30355e35-4f3c-4dc0-942a-0ac824fb40b3 | cc-by-4.0 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | e2963d6d-79ab-4550-9aec-c58cc2a16fcc | cc-by-4.0 |
End of preview. Expand in Data Studio
Dataset Description:
Nemotron-SFT-SWE-v3 is a software engineering instruction tuning dataset designed to advance the capabilities of LLMs on SWE-Bench style tasks. It includes agentic trajectories collected using a variety of agent harnesses, including the OpenHands, SWE-agent, and mini-SWE-agent frameworks.
This dataset is ready for commercial use.
Dataset Owner(s):
NVIDIA Corporation
Dataset Creation Date:
Created on: 2026-06-04
Last Modified on: 2026-06-04
License/Terms of Use:
This dataset is licensed under Creative Commons Attribution 4.0 International (CC-BY 4.0).
Additional Information: Apache 2.0 License; MIT License; BSD-3 License; BSD-2 License.
Intended Usage:
This dataset is intended for LLM engineers and research teams building autonomous software engineering agents and code-focused assistants. It is suitable for supervised fine-tuning and distillation of models that must interpret real-world issue statements, plan multi-step tool use, navigate codebases, and implement fixes in a SWE-Bench–style setting. The trajectories can also be used to benchmark and debug agent policies, improve repository-aware reasoning, and study robust, regression-free code editing behaviors in both academic and production environments.
Dataset Characterization
Data Collection Method
Hybrid: Automated, Synthetic
Labeling Method
Hybrid: Automated, Synthetic
Dataset Format
Modality: Text
Format: JSONL
Structure: Text + Metadata
Dataset Quantification
| Subset | Samples |
|---|---|
| Total | 237,970 |
Total Data Storage: ~11.7GB
Reference(s):
- Training Software Engineering Agents and Verifiers with SWE-Gym
- R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
- SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
- The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
- Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have 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 developer teams to ensure this dataset meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here
- Downloads last month
- 103
Collections including nvidia/Nemotron-SFT-SWE-v3
Papers for nvidia/Nemotron-SFT-SWE-v3
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Paper • 2512.13607 • Published • 39
The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
Paper • 2511.03690 • Published • 1
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
Paper • 2505.20411 • Published • 96
R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
Paper • 2504.07164 • Published • 2
Training Software Engineering Agents and Verifiers with SWE-Gym
Paper • 2412.21139 • Published • 26