{
  "id": "redpajama-incite-7b-base",
  "name": "RedPajama-INCITE-7B-Base",
  "identifiers": {
    "huggingface": [
      "togethercomputer/RedPajama-INCITE-7B-Base"
    ]
  },
  "developer": "Together Computer (with Ontocord.ai, ETH DS3Lab, Stanford CRFM, Université de Montréal)",
  "release_date": {
    "value": "2023-05-04",
    "source": "https://huggingface.co/api/models/togethercomputer/RedPajama-INCITE-7B-Base",
    "status": "partial",
    "note": "HF repo creation date; may predate or postdate public release."
  },
  "weights_status": "open",
  "availability": {
    "value": "available",
    "checked": "2026-09-24",
    "source": "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base"
  },
  "license": {
    "value": "apache-2.0",
    "source": "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base/blob/78f7e482443971f4873ba3239f0ac810a367833b/README.md",
    "status": "partial",
    "note": "From HF card metadata (uploader-declared); confirm against the license text."
  },
  "architecture": {
    "family": "decoder_only",
    "note": "Card/tags: GPT-NeoX architecture. Config was not independently checked for rotary_pct/positional encoding this session.",
    "n_layers": {
      "value": 32,
      "source": "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base/raw/78f7e482443971f4873ba3239f0ac810a367833b/config.json",
      "status": "recorded"
    },
    "hidden_size": {
      "value": 4096,
      "source": "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base/raw/78f7e482443971f4873ba3239f0ac810a367833b/config.json",
      "status": "recorded"
    },
    "n_heads": {
      "value": 32,
      "source": "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base/raw/78f7e482443971f4873ba3239f0ac810a367833b/config.json",
      "status": "recorded"
    },
    "vocab_size": {
      "value": 50432,
      "source": "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base/raw/78f7e482443971f4873ba3239f0ac810a367833b/config.json",
      "status": "recorded"
    },
    "context_length": {
      "value": 2048,
      "source": "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base/raw/78f7e482443971f4873ba3239f0ac810a367833b/config.json",
      "status": "recorded"
    },
    "positional_encoding": {
      "value": null,
      "status": "not_recorded"
    }
  },
  "training_data": {
    "value": "RedPajama-Data-1T (~1 trillion tokens), a reproduction of the LLaMA training mix. Card, Training Data: 'Please refer to togethercomputer/RedPajama-Data-1T'; Num of Tokens: 1.001T.",
    "source": "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base/blob/78f7e482443971f4873ba3239f0ac810a367833b/README.md",
    "status": "recorded"
  },
  "techniques": [],
  "primary_sources": [
    "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base",
    "https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base/raw/78f7e482443971f4873ba3239f0ac810a367833b/config.json"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "ingested as candidate from HF (togethercomputer/RedPajama-INCITE-7B-Base@78f7e482443971f4873ba3239f0ac810a367833b)",
      "by": "ingest_hf.py"
    },
    {
      "date": "2026-09-24",
      "change": "preparer: developer set; dataset edge rejected pending a RedPajama record",
      "by": "claude (preparer, Sonnet 5)"
    },
    {
      "date": "2026-09-24",
      "change": "preparer cleanup: removed 2 stale flag(s), filled training_data",
      "by": "claude (preparer, Sonnet 5)"
    },
    {
      "date": "2026-09-24",
      "change": "reviewed and promoted from staging (0 edge(s) accepted)",
      "by": "Wilson Pruitt"
    },
    {
      "date": "2026-09-24",
      "change": "trained_on redpajama-data-1t added now the dataset record exists",
      "by": "wilson-pruitt + claude"
    }
  ]
}