{"slug":"curator","name":"Curator","category":"training","categoryName":"Training & fine-tuning","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://github.com/NVIDIA-NeMo/Curator","repo":"https://github.com/NVIDIA-NeMo/Curator","latestVersion":"v1.4.0","latestRelease":"2026-10-09","stars":1818,"starsAsOf":"2026-10-22","description":"Scalable data pre processing and curation toolkit for LLMs","descriptionZh":"大规模数据整理","callMethods":["SDK"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["data","data-curation","data-prep","data-preparation","data-processing","data-processing-pipelines","data-quality","datacuration","datarecipes","deduplication","fast-data-processing","fine-tuning","large-language-models","large-scale-data-processing","llm","llm-data-quality","llmapps","python","semantic-deduplication"],"language":"Python","lastPush":"2026-10-21","formerly":"nvidia/nemo-curator","packages":[],"recentVersions":[{"version":"v1.4.0","date":"2026-10-09","prerelease":false,"url":"https://github.com/NVIDIA-NeMo/Curator/releases/tag/v1.4.0","source":"GitHub Release"},{"version":"v1.3.0","date":"2026-07-27","prerelease":false,"url":"https://github.com/NVIDIA-NeMo/Curator/releases/tag/v1.3.0","source":"GitHub Release"},{"version":"v1.2.0","date":"2026-05-14","prerelease":false,"url":"https://github.com/NVIDIA-NeMo/Curator/releases/tag/v1.2.0","source":"GitHub Release"},{"version":"v1.1.0","date":"2026-02-23","prerelease":false,"url":"https://github.com/NVIDIA-NeMo/Curator/releases/tag/v1.1.0","source":"GitHub Release"},{"version":"v1.0.0","date":"2025-10-01","prerelease":false,"url":"https://github.com/NVIDIA-NeMo/Curator/releases/tag/v1.0.0","source":"GitHub Release"}],"alternatives":["unsloth","llamafactory","peft","trainer","transformers","litgpt","axolotl","cleanlab"],"stacks":[],"scenarios":[],"problems":[],"reasonZh":"开源大库收录：大规模数据整理","sources":["oss","github-pool"],"record":"https://aimap.page/api/v1/software/curator.json","pages":{"en":"https://aimap.page/en/software/curator/","zh-hans":"https://aimap.page/zh-hans/software/curator/"}}