{
  "id": "baize-v2-7b",
  "name": "Baize v2 7B",
  "identifiers": {
    "huggingface": [
      "project-baize/baize-v2-7b"
    ]
  },
  "developer": "Project Baize (UC San Diego; Sun Yat-sen University)",
  "release_date": {
    "value": "2023-05-23",
    "source": "https://github.com/project-baize/baize-chatbot/blob/main/README.md",
    "status": "recorded",
    "note": "Project README, dated entry: '[May 23, 2023] We are releasing Baize v2! Check out the 7B and 13B model.' HF repo creation date matches."
  },
  "weights_status": "open",
  "availability": {
    "value": "available",
    "checked": "2026-09-24",
    "source": "https://huggingface.co/project-baize/baize-v2-7b"
  },
  "license": {
    "value": "cc-by-nc-4.0",
    "source": "https://huggingface.co/project-baize/baize-v2-7b/blob/e4731c2c2671e2d0b47b5eba08c753ca21671fab/README.md",
    "status": "partial",
    "note": "Card metadata only (`license: cc-by-nc-4.0`); the card carries no separate license text. The weights are merged with LLaMA, whose own terms are not addressed on the card."
  },
  "architecture": {
    "family": "decoder_only",
    "note": "family read from config 'architectures': ['LlamaForCausalLM'].",
    "n_layers": {
      "value": 32,
      "source": "https://huggingface.co/project-baize/baize-v2-7b/raw/e4731c2c2671e2d0b47b5eba08c753ca21671fab/config.json",
      "status": "recorded"
    },
    "hidden_size": {
      "value": 4096,
      "source": "https://huggingface.co/project-baize/baize-v2-7b/raw/e4731c2c2671e2d0b47b5eba08c753ca21671fab/config.json",
      "status": "recorded"
    },
    "n_heads": {
      "value": 32,
      "source": "https://huggingface.co/project-baize/baize-v2-7b/raw/e4731c2c2671e2d0b47b5eba08c753ca21671fab/config.json",
      "status": "recorded"
    },
    "vocab_size": {
      "value": 32000,
      "source": "https://huggingface.co/project-baize/baize-v2-7b/raw/e4731c2c2671e2d0b47b5eba08c753ca21671fab/config.json",
      "status": "recorded"
    },
    "context_length": {
      "value": 2048,
      "source": "https://huggingface.co/project-baize/baize-v2-7b/raw/e4731c2c2671e2d0b47b5eba08c753ca21671fab/config.json",
      "status": "recorded"
    },
    "positional_encoding": {
      "value": "rotary (RoPE)",
      "source": "https://arxiv.org/abs/2302.13971",
      "status": "recorded",
      "note": "Propagated from llama-7b: the card says the LoRA-tuned checkpoint 'has been merged with LLaMA' and neither card nor paper describes an architecture change."
    }
  },
  "training_data": {
    "value": "Baize self-chat dialogues (ChatGPT chatting with itself) plus Alpaca data, per the project README for the Baize family; the v2 card says only that the model was 'trained with supervised fine-tuning (SFT) and self-distillation with feedback (SDF)'. The exact v2 data mixture is not stated.",
    "source": "https://github.com/project-baize/baize-chatbot/blob/main/README.md",
    "status": "partial",
    "note": "README: 'It uses 100k dialogs generated by letting ChatGPT chat with itself. We also use Alpaca's data to improve its performance.' The README's own training command (alpaca,stackoverflow,quora) is for the v1 sizes."
  },
  "techniques": [],
  "primary_sources": [
    "https://huggingface.co/project-baize/baize-v2-7b",
    "https://huggingface.co/project-baize/baize-v2-7b/blob/e4731c2c2671e2d0b47b5eba08c753ca21671fab/README.md",
    "https://arxiv.org/abs/2304.01196",
    "https://github.com/project-baize/baize-chatbot/blob/main/README.md",
    "https://huggingface.co/project-baize/baize-v2-7b/raw/e4731c2c2671e2d0b47b5eba08c753ca21671fab/config.json"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "ingested as candidate from HF (project-baize/baize-v2-7b@e4731c2c2671e2d0b47b5eba08c753ca21671fab)",
      "by": "ingest_hf.py"
    },
    {
      "date": "2026-09-24",
      "change": "preparer: developer, release date (README), positional encoding (propagated from llama-7b), training data (partial), 3 edges prepared + 1 PANEL-NEEDED; sources: card, README, arXiv 2304.01196",
      "by": "claude (preparer, Sonnet 5)"
    },
    {
      "date": "2026-09-24",
      "change": "ruling: Wilson, after 3-tier panel split (no majority), see session log: baize-sdf stub; trained_on baize-sdf added, direct feedback_from chatgpt rejected",
      "by": "claude (preparer, Sonnet 5)"
    },
    {
      "date": "2026-09-24",
      "change": "reviewed and promoted from staging (3 edge(s) accepted)",
      "by": "Wilson Pruitt"
    }
  ]
}