{
  "baseModel": "perplexity-ai/PII-Tracer",
  "baseRevision": "d25c16f2e57e321f6d2527715c01df9112f956f5",
  "convertedWith": "medikit packages/pii-portal/tools/pii-tracer",
  "opset": 20,
  "inputs": {
    "input_ids": "int64 [batch, sequence]"
  },
  "outputs": {
    "logits": "float32 [batch, sequence, 37]",
    "sensitivity": "float32 [batch, 1]"
  },
  "maxSequenceLength": 4096,
  "piiTypes": [
    "private_person",
    "private_email",
    "private_phone",
    "private_address",
    "private_url",
    "private_date",
    "account_number",
    "secret",
    "other_pii"
  ],
  "labels": [
    "O",
    "B-private_person",
    "I-private_person",
    "E-private_person",
    "S-private_person",
    "B-private_email",
    "I-private_email",
    "E-private_email",
    "S-private_email",
    "B-private_phone",
    "I-private_phone",
    "E-private_phone",
    "S-private_phone",
    "B-private_address",
    "I-private_address",
    "E-private_address",
    "S-private_address",
    "B-private_url",
    "I-private_url",
    "E-private_url",
    "S-private_url",
    "B-private_date",
    "I-private_date",
    "E-private_date",
    "S-private_date",
    "B-account_number",
    "I-account_number",
    "E-account_number",
    "S-account_number",
    "B-secret",
    "I-secret",
    "E-secret",
    "S-secret",
    "B-other_pii",
    "I-other_pii",
    "E-other_pii",
    "S-other_pii"
  ],
  "variants": [
    {
      "id": "q8",
      "default": true,
      "file": "onnx/model.onnx",
      "externalData": [
        "onnx/model.onnx_data"
      ],
      "bytes": 615736663,
      "weights": "8-bit MatMulNBits, block 128, integer zero point; int8 embedding; fp32 heads",
      "executionProviders": [
        "webgpu",
        "wasm"
      ],
      "argmaxAgreementVsFp32": 1.0,
      "note": "The variant to use in a browser. onnxruntime-web's WebGPU kernels run this one on the GPU."
    },
    {
      "id": "q4",
      "default": false,
      "file": "onnx/model_q4.onnx",
      "externalData": [
        "onnx/model_q4.onnx_data"
      ],
      "bytes": 488434478,
      "weights": "4-bit MatMulNBits, block 32, float zero point; int8 embedding; fp32 heads",
      "executionProviders": [
        "wasm"
      ],
      "argmaxAgreementVsFp32": 0.981,
      "note": "Smaller, and needs float zero points: at 4 bits an integer zero point collapses this checkpoint, because only a float one reproduces each block's extremes exactly. onnxruntime-web's WebGPU MatMulNBits kernels have no float zero-point path, so every matmul falls back to the CPU and it runs about 15x slower than q8 there."
    }
  ]
}