{
  "claim": "ZDTaichu5.0-9B ships 9,794,197,512 parameters in 19,588,395,036 tensor bytes across five safetensors shards. Every shard's real size, tensor list and parameter count was recovered by HTTP range read without downloading any weights, and the three totals reconcile exactly: 8 length bytes per file, plus 106,344 bytes of JSON headers, plus tensor bytes, equals the sum of the CDN's Content-Length values to the byte.",
  "method": "For each shard: curl -sSL -I <resolve URL> to follow the xet CDN redirect and read Content-Length; then Range: bytes=0-7 for the little-endian u64 header length, then Range: bytes=8-(8+n-1) for the JSON header. Parameter counts are the product of each tensor's shape; byte counts are data_offsets[1]-data_offsets[0].",
  "source": "https://huggingface.co/TaichuAI/ZDTaichu5.0-9B",
  "captured": "2026-09-18",
  "columns": [
    {
      "key": "shard",
      "label": "file",
      "align": "left"
    },
    {
      "key": "content_length",
      "label": "CDN Content-Length (B)",
      "align": "right"
    },
    {
      "key": "lfs_pointer",
      "label": "git-lfs pointer size (B)",
      "align": "right"
    },
    {
      "key": "header_bytes",
      "label": "safetensors header (B)",
      "align": "right"
    },
    {
      "key": "tensors",
      "label": "tensors",
      "align": "right"
    },
    {
      "key": "params",
      "label": "parameters",
      "align": "right"
    }
  ],
  "rows": [
    {
      "shard": "model-1-of-5.safetensors",
      "content_length": 4268658872,
      "lfs_pointer": 4268658872,
      "header_bytes": 9776,
      "tensors": 75,
      "params": 2134324544
    },
    {
      "shard": "model-2-of-5.safetensors",
      "content_length": 4265727128,
      "lfs_pointer": 4265727128,
      "header_bytes": 16656,
      "tensors": 128,
      "params": 2132855232
    },
    {
      "shard": "model-3-of-5.safetensors",
      "content_length": 4215379968,
      "lfs_pointer": 4215379968,
      "header_bytes": 16760,
      "tensors": 128,
      "params": 2107681600
    },
    {
      "shard": "model-4-of-5.safetensors",
      "content_length": 3123658752,
      "lfs_pointer": 3123658752,
      "header_bytes": 12408,
      "tensors": 95,
      "params": 1561823168
    },
    {
      "shard": "model-5-of-5.safetensors",
      "content_length": 3715076700,
      "lfs_pointer": 3715076700,
      "header_bytes": 50744,
      "tensors": 394,
      "params": 1857512968
    },
    {
      "shard": "— total —",
      "content_length": 19588501420,
      "lfs_pointer": 19588501420,
      "header_bytes": 106344,
      "tensors": 820,
      "params": 9794197512
    }
  ],
  "note": "The index file's declared metadata.total_size is 19,588,395,036, which is tensor bytes only and excludes headers — it matches the summed data_offsets exactly, so nothing is missing or double-counted. The parameter total splits into 8,953,803,264 in the language model, 651,645,448 in the C-RADIOv4-H vision tower (390 tensors, one of them an int64 index buffer) and 188,748,800 in the mlp1 projector. config.json labels the release \"9B\" via _model_size_label; the shipped artifact is 9.79B, of which 2,034,237,440 (20.8%) is the untied input embedding plus LM head over a 248,320-token vocabulary."
}