queen-v4 / version.json
Crawlnet's picture
the x1.5 branch's own plan: 945M tokens trained
402944a verified
Raw History Blame Contribute Delete
1.09 kB
{
"version": 4,
"datasetTokens": 183061543,
"datasetPages": 142428,
"params": 185598434,
"trainedAt": "2026-10-08T13:08:00+00:00",
"weightsUrl": "https://huggingface.co/Crawlnet/queen-v4",
"name": "queen-v4",
"paramsNonEmbedding": 97518000,
"tokensTrained": 945029120,
"epochs": 5.16,
"valBpb": 1.4380317966698843,
"sftMethod": "synthetic+openbook",
"datasetManifestSha256": "6792bfb740b3c7217663afdba60ae75f5ae6d79aa53ac1475971fabe51a981ac",
"costUsd": 2.09,
"gpuHours": 6.151,
"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": 96801
},
"records": {
"pages": 45627,
"tokensApprox": 10830251,
"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)"
}
}
}