{
  "id": "openorca",
  "name": "OpenOrca",
  "identifiers": {
    "huggingface": [
      "Open-Orca/OpenOrca"
    ]
  },
  "builder": "Open-Orca (community group)",
  "release_date": {
    "value": "2023-06-15",
    "source": "https://huggingface.co/api/datasets/Open-Orca/OpenOrca",
    "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/Open-Orca/OpenOrca"
  },
  "content": {
    "value": "Card: 'a collection of augmented FLAN Collection data ... Currently ~1M GPT-4 completions, and ~3.2M GPT-3.5 completions', tabularized to align with the distributions in the Orca paper (arXiv 2306.02707). The card calls it 'a partial completion of the full intended dataset'.",
    "source": "https://huggingface.co/datasets/Open-Orca/OpenOrca",
    "status": "recorded"
  },
  "primary_sources": [
    "https://huggingface.co/datasets/Open-Orca/OpenOrca",
    "https://arxiv.org/abs/2306.02707"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "created from primary sources (tranche 2 dataset records)",
      "by": "wilson-pruitt + claude"
    }
  ]
}