{
  "metadata_version": "0.2",
  "kind": "decision-head",
  "name": "clef_flash_head_bucket_fp16w32",
  "assets": {
    "main": "clef_flash_head_bucket_fp16w32.aimodel"
  },
  "head": {
    "graph": "conversion/clef_flash/clef_head.py ClefHeadGraph: the author's JointSchemaHead for one record, tensor inputs only",
    "shape": "bucket",
    "functions": [
      "t512",
      "t1024",
      "t2048",
      "t4096"
    ],
    "buckets": [
      [
        "t512",
        512
      ],
      [
        "t1024",
        1024
      ],
      [
        "t2048",
        2048
      ],
      [
        "t4096",
        4096
      ]
    ],
    "dims": null,
    "host_pad": "bucket",
    "host_pad_rule": "T to the smallest bucket >= T (512, 1024, 2048, 4096), Q to 16, O to 128; padding rows / columns zero, their valid flags 0",
    "inputs": {
      "hidden": "[T, 4096] f32",
      "key_valid": "[T] f32",
      "q_avg": "[Q, T] f32",
      "o_avg": "[O, T] f32",
      "g_avg": "[1, T] f32",
      "lexical": "[O, 4096] f32",
      "member": "[Q, O] f32",
      "type_ids": "[Q] i32",
      "q_valid": "[Q] f32",
      "o_valid": "[O] f32"
    },
    "input_order": [
      "hidden",
      "key_valid",
      "q_avg",
      "o_avg",
      "g_avg",
      "lexical",
      "member",
      "type_ids",
      "q_valid",
      "o_valid"
    ],
    "outputs": {
      "logits": "[O] f32; padding options 0"
    },
    "weights": "fp16w32",
    "softmax": "host: per question, fp32, over that question's options",
    "lexical": "host: lm_head_fp16.bin rows of each option span's ids, averaged (clef_head.lexical_rows)",
    "source": {
      "hf_id": "Cloudflare/clef-flash",
      "revision": "17f0b0ad64efb65d273590632833508766b2aae6",
      "joint_schema_model_sha256": "0e304cf7c6500e8bb59bef7e2afd2c6373f82596dfb3b57d1aa93c175e2dc3a3",
      "joint_head_safetensors_sha256": "19cdcec8c81dc9212be320fff47462ab342fbc1278be4368fb3da71241cf5ba0",
      "joint_head_config_sha256": "77efe959a38b5b17b241543e129e695f3c77465ece55a25985279bd8176279a0"
    }
  },
  "export": {
    "aimodel_bytes": 243979102,
    "main_mlirb": {
      "bytes": 243978965,
      "sha256": "51e512ad1e4d3bcfdc7af43c1100124bd94d539de01f09651afc9b98486856fe"
    },
    "seconds": {
      "build": 0.19440945898531936,
      "export": 10.82508116599638,
      "optimize": 0.031602208997355774,
      "save": 0.2501100410008803,
      "total": 11.301202874979936
    },
    "export_attempts": [
      {
        "externalize": "default externalize specs",
        "ok": true,
        "seconds": 9.44808970799204
      }
    ]
  },
  "aot": {
    "note": "compiled for the gates with: xcrun coreai-build compile <this .aimodel> --output <dir> --platform macOS --preferred-compute gpu --architecture h16c (not shipped; the Swift host specializes the .aimodel)",
    "flags": [
      "--platform",
      "macOS",
      "--preferred-compute",
      "gpu",
      "--architecture",
      "h16c"
    ],
    "seconds": 0.5527557500172406
  },
  "compilation": {
    "date": "2026-10-03T13:53:31+09:00",
    "targets": [
      "h16c"
    ]
  }
}