version.json

{
  "version": 2,
  "datasetTokens": 75776124,
  "datasetPages": 79202,
  "params": 75497898,
  "trainedAt": "2026-10-05T11:33:44+00:00",
  "weightsUrl": "https://huggingface.co/Crawlnet/queen-v2",
  "name": "queen-v2",
  "paramsNonEmbedding": 33554816,
  "tokensTrained": 352321536,
  "epochs": 4.65,
  "valBpb": 1.0196070539881081,
  "sftMethod": "synthetic+openbook:deepseek-flash",
  "datasetManifestSha256": "4ba917bb50964b231dcca9e641822941975260afb51ef87f34101958cd50e042",
  "costUsd": 0.25,
  "gpuHours": 0.725,
  "gpu": "1 GPU (our GPU server)",
  "nanochatCommit": "92d63d4e8bb4df75c3b71618f31ddde2378b2bcd",
  "toy": false,
  "tokenizer": "trained on this dataset only (crawler pages and record pages)",
  "license": "apache-2.0",
  "datasetSources": {
    "crawl": {
      "pages": 34234
    },
    "records": {
      "pages": 44968,
      "tokensApprox": 9707932,
      "what": "public market, funding and on-chain records (projects and their funding rounds, investors, token unlocks and token facts, DeFi protocols, chains and stablecoins, DEX and on-chain token statistics)"
    }
  }
}