{
  "id": "starling-lm-7b-alpha",
  "name": "Starling-LM-7B-alpha",
  "identifiers": {
    "huggingface": [
      "berkeley-nest/Starling-LM-7B-alpha"
    ]
  },
  "developer": "Banghua Zhu, Evan Frick, Tianhao Wu, Hanlin Zhu and Jiantao Jiao (Berkeley NEST; card 'Developed by')",
  "release_date": {
    "value": "2023-11-25",
    "source": "https://huggingface.co/api/models/berkeley-nest/Starling-LM-7B-alpha",
    "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/berkeley-nest/Starling-LM-7B-alpha"
  },
  "license": {
    "value": "Apache-2.0 per card metadata and model summary, 'under the condition that the model is not used to compete with OpenAI'; the card's License section also says research preview, non-commercial, subject to LLaMA/OpenAI/ShareGPT terms",
    "source": "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/blob/1dddf3b95bc1391f6307299eb1c162c194bde9bd/README.md",
    "status": "partial",
    "note": "The card contradicts itself: metadata `license: apache-2.0` and 'License: Apache-2.0 license under the condition that the model is not used to compete with OpenAI', but the later License section: 'research preview intended for non-commercial use only, subject to the data distillation License of LLaMA, Terms of Use of the data generated by OpenAI, and Privacy Practices of ShareGPT'. Not reconciled; reviewer check."
  },
  "architecture": {
    "family": "decoder_only",
    "note": "family read from config 'architectures': ['MistralForCausalLM'].",
    "n_layers": {
      "value": 32,
      "source": "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/raw/1dddf3b95bc1391f6307299eb1c162c194bde9bd/config.json",
      "status": "recorded"
    },
    "hidden_size": {
      "value": 4096,
      "source": "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/raw/1dddf3b95bc1391f6307299eb1c162c194bde9bd/config.json",
      "status": "recorded"
    },
    "n_heads": {
      "value": 32,
      "source": "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/raw/1dddf3b95bc1391f6307299eb1c162c194bde9bd/config.json",
      "status": "recorded"
    },
    "vocab_size": {
      "value": 32002,
      "source": "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/raw/1dddf3b95bc1391f6307299eb1c162c194bde9bd/config.json",
      "status": "recorded"
    },
    "context_length": {
      "value": 8192,
      "source": "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/raw/1dddf3b95bc1391f6307299eb1c162c194bde9bd/config.json",
      "status": "recorded"
    },
    "n_kv_heads": {
      "value": 8,
      "source": "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/raw/1dddf3b95bc1391f6307299eb1c162c194bde9bd/config.json",
      "status": "recorded"
    },
    "positional_encoding": {
      "value": "rotary (RoPE)",
      "source": "https://github.com/mistralai/mistral-src/blob/c18d5b9166ffa16ce58827346ed56a28d2876e7e/one_file_ref.py",
      "status": "recorded",
      "note": "Architecture unchanged from mistral-7b-v0-1 (fine-tune, not a structural change)."
    }
  },
  "training_data": {
    "value": "Nectar (GPT-4-ranked 7-wise comparisons) used to train the reward model Starling-RM-7B-alpha (fine-tuned from Llama2-7B-Chat); the policy was then tuned from OpenChat 3.5 against that reward model with advantage-induced policy alignment (APA).",
    "source": "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/blob/1dddf3b95bc1391f6307299eb1c162c194bde9bd/README.md",
    "status": "partial",
    "note": "Card: 'trained from Openchat 3.5 with reward model berkeley-nest/Starling-RM-7B-alpha and policy optimization method APA'. Blog (starling.cs.berkeley.edu): 'training a reward model and conducting online RL based on the existing Nectar Dataset'; 'Our reward model is fine-tuned from Llama2-7B-Chat'. Whether the policy's own prompts came from Nectar is not stated in the sources read."
  },
  "techniques": [],
  "primary_sources": [
    "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha",
    "https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/raw/1dddf3b95bc1391f6307299eb1c162c194bde9bd/config.json"
  ],
  "record_history": [
    {
      "date": "2026-09-24",
      "change": "ingested as candidate from HF (berkeley-nest/Starling-LM-7B-alpha@1dddf3b95bc1391f6307299eb1c162c194bde9bd)",
      "by": "ingest_hf.py"
    },
    {
      "date": "2026-09-24",
      "change": "preparer: developer, license (partial), training data (partial), positional encoding (propagated), 2 edges (fine_tuned_from openchat-3-5; trained_on nectar left PANEL-NEEDED); sources: card, Starling blog",
      "by": "claude (preparer, Sonnet 5)"
    },
    {
      "date": "2026-09-24",
      "change": "ruling: 3-tier panel (3/3, feedback_from via reward-model record), see session log: trained_on nectar rejected, feedback_from starling-rm-7b-alpha added; evidence tags set to declared (uploader is the developer)",
      "by": "wilson-pruitt + claude (Sonnet 5)"
    },
    {
      "date": "2026-09-24",
      "change": "reviewed and promoted from staging (2 edge(s) accepted)",
      "by": "Wilson Pruitt"
    }
  ]
}