{
  "id": "baize",
  "name": "Baize self-chat data",
  "identifiers": {},
  "builder": "UC San Diego / Sun Yat-sen University (Baize authors)",
  "release_date": {
    "value": "2023-04-03",
    "source": "https://arxiv.org/abs/2304.01196",
    "status": "partial",
    "note": "arXiv v1 date of the Baize paper."
  },
  "availability": {
    "value": "available",
    "checked": "2026-09-24",
    "source": "https://github.com/project-baize/baize-chatbot/tree/main/data",
    "note": "Data lives in the project's GitHub repo, not on Hugging Face; the repo data folder returned HTTP 200. No HF dataset repo id was confirmed (project-baize/baize-chatbot is not a dataset)."
  },
  "content": {
    "value": "Paper: dialogues produced by having ChatGPT chat with itself ('self-chat') from seed questions from Quora and Stack Overflow; 'we collect a total of 111.5k dialogues through self-chat, using ∼55k questions' for the v1 family. Repo README lists 54K/57K/47K dialogs from Quora, StackOverflow and MedQuAD questions. Falcon-7B/40B-instruct's card lists Baize as part of their fine-tuning mix.",
    "source": "https://arxiv.org/abs/2304.01196",
    "status": "recorded",
    "note": "Counts are the paper's and the README's; the released files were not counted."
  },
  "primary_sources": [
    "https://arxiv.org/abs/2304.01196",
    "https://github.com/project-baize/baize-chatbot"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "created from primary sources (tranche 2 dataset records)",
      "by": "wilson-pruitt + claude"
    }
  ]
}