{
  "id": "starcoder",
  "name": "StarCoder",
  "identifiers": {
    "huggingface": [
      "bigcode/starcoder"
    ]
  },
  "developer": "BigCode project (open scientific collaboration led jointly by Hugging Face and ServiceNow Research)",
  "release_date": {
    "value": "2023-05-04",
    "source": "https://huggingface.co/blog/starcoder",
    "status": "recorded",
    "note": "Release post published May 4, 2023 announces StarCoder and StarCoderBase together. HF repo created 2023-04-24 (access-gated, likely pre-release)."
  },
  "weights_status": "open",
  "availability": {
    "value": "gated",
    "checked": "2026-09-24",
    "source": "https://huggingface.co/bigcode/starcoder",
    "note": "HF gate: auto."
  },
  "license": {
    "value": "BigCode OpenRAIL-M v1",
    "source": "https://huggingface.co/bigcode/starcoder/blob/827cd7721231872c152e3faef5cae1b22964ed58/README.md",
    "status": "recorded",
    "note": "Card metadata `license: bigcode-openrail-m`; paper: 'We release StarCoder under an OpenRAIL-M license agreement'."
  },
  "architecture": {
    "family": "decoder_only",
    "note": "Config.json is gated (not retrievable). Values from the StarCoder paper Table 11 and section 5.2; the paper states multi-query attention (a single shared key/value head by definition; the paper gives no count) and 'learned absolute positional embeddings'. Fine-tuning (StarCoder from StarCoderBase) changes no architecture field.",
    "n_layers": {
      "value": 40,
      "source": "https://arxiv.org/abs/2305.06161",
      "status": "recorded",
      "note": "Paper Table 11 'Num. of hidden layers'."
    },
    "hidden_size": {
      "value": 6144,
      "source": "https://arxiv.org/abs/2305.06161",
      "status": "recorded",
      "note": "Paper Table 11."
    },
    "n_heads": {
      "value": 48,
      "source": "https://arxiv.org/abs/2305.06161",
      "status": "recorded",
      "note": "Paper Table 11 'Num. of attention heads'."
    },
    "vocab_size": {
      "value": 49152,
      "source": "https://arxiv.org/abs/2305.06161",
      "status": "recorded",
      "note": "Paper sec. 5.1: 'vocabulary size of 49,152 tokens—including the sentinel tokens'. WizardCoder's HF config shows 49,153 (one added token)."
    },
    "positional_encoding": {
      "value": "learned absolute",
      "source": "https://arxiv.org/abs/2305.06161",
      "status": "recorded",
      "note": "Paper sec. 5.2: 'decoder-only Transformer with Multi-Query-Attention, and learned absolute positional embeddings'."
    },
    "context_length": {
      "value": 8192,
      "source": "https://arxiv.org/abs/2305.06161",
      "status": "recorded",
      "note": "Paper Table 11 'Max. position embeddings' 8192; card: 'a context window of 8192 tokens'."
    }
  },
  "training_data": {
    "value": "StarCoderBase (1T tokens, The Stack v1.2), then fine-tuned for 2 epochs on the Python subset of the training data: 35B Python tokens.",
    "source": "https://arxiv.org/abs/2305.06161",
    "status": "recorded",
    "note": "Paper: 'We fine-tuned StarCoderBase on another 35B Python tokens, resulting in the creation of StarCoder'; sec. 5.6 'Starting from StarCoderBase, we fine-tuned a Python variant of the model for 2 epochs on the Python subset of the training data ... 8,500 steps'."
  },
  "techniques": [],
  "primary_sources": [
    "https://huggingface.co/bigcode/starcoder"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "ingested as candidate from HF (bigcode/starcoder@827cd7721231872c152e3faef5cae1b22964ed58)",
      "by": "ingest_hf.py"
    },
    {
      "date": "2026-09-24",
      "change": "preparer: developer, release date (blog), license, architecture (paper), training data, 3 edge entries (fine_tuned_from starcoderbase; trained_on starcoderdata; the-stack-dedup rejected); sources: card, arXiv 2305.06161, release post, dataset API",
      "by": "claude (preparer, Sonnet 5)"
    },
    {
      "date": "2026-09-24",
      "change": "reviewed and promoted from staging (2 edge(s) accepted)",
      "by": "Wilson Pruitt"
    }
  ]
}