{
  "id": "redpajama-data-instruct",
  "name": "RedPajama-Data-Instruct",
  "identifiers": {
    "huggingface": [
      "togethercomputer/RedPajama-Data-Instruct"
    ]
  },
  "builder": "Together Computer",
  "release_date": {
    "value": "2023-06-05",
    "source": "https://huggingface.co/api/datasets/togethercomputer/RedPajama-Data-Instruct",
    "status": "partial",
    "note": "HF dataset repo creation date, not the builder's own release announcement."
  },
  "availability": {
    "value": "available",
    "checked": "2026-09-24",
    "source": "https://huggingface.co/datasets/togethercomputer/RedPajama-Data-Instruct"
  },
  "content": {
    "value": "Card: 'curated from a diverse collection of NLP tasks from both P3 (BigScience) and Natural Instruction (AI2)', decontaminated against HELM: 'we filtered out 137 tasks and 5.2M instances (out of 1069 tasks and 93.3M instances)'.",
    "source": "https://huggingface.co/datasets/togethercomputer/RedPajama-Data-Instruct",
    "status": "recorded"
  },
  "primary_sources": [
    "https://huggingface.co/datasets/togethercomputer/RedPajama-Data-Instruct"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "created from primary sources (tranche 2 dataset records)",
      "by": "wilson-pruitt + claude"
    }
  ]
}