{
  "id": "oig",
  "name": "Open Instruction Generalist (OIG)",
  "identifiers": {
    "huggingface": [
      "laion/OIG"
    ]
  },
  "builder": "LAION",
  "release_date": {
    "value": "2023-03-05",
    "source": "https://huggingface.co/api/datasets/laion/OIG",
    "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/laion/OIG",
    "note": "Card advises downloading the individual jsonl files rather than using load_dataset."
  },
  "content": {
    "value": "Card: 'a large instruction dataset of medium quality along with a smaller high quality instruction dataset (OIG-small-chip2)'; 'OIG is currently at 44M' instructions. The card does not say which parts were model-generated, so no model-parent edge is recorded.",
    "source": "https://huggingface.co/datasets/laion/OIG",
    "status": "partial",
    "note": "The card describes a growing collection; the size is as of the card text read on this date."
  },
  "primary_sources": [
    "https://huggingface.co/datasets/laion/OIG"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "created from primary sources (tranche 2 dataset records)",
      "by": "wilson-pruitt + claude"
    }
  ]
}