{
  "model_name": "ABEJA-Qwen2.5-7b-Japanese-QNN",
  "version": "1.0.0",
  "description": "ABEJA Qwen 2.5 7B Japanese model compiled for Qualcomm QNN (Mock)",
  "language": "japanese",
  "hardware_target": "Qualcomm NPU (Snapdragon 8cx Gen 2+)",
  "quantization": "INT8",
  "models": {
    "prefill": {
      "path": "prefill/",
      "description": "Prefill model for initial token generation"
    },
    "token_generation": {
      "path": "token_gen/",
      "description": "Token generation model for subsequent tokens"
    }
  },
  "requirements": {
    "qnn_sdk_version": "2.18.0.240127",
    "onnxruntime_qnn": "latest",
    "python_version": ">=3.8"
  },
  "usage": {
    "inference": "Use onnxruntime-qnn with QNNExecutionProvider",
    "deployment": "Deploy to Qualcomm NPU hardware"
  },
  "notes": "This is a mock QNN compilation for demonstration. Real deployment requires QNN SDK installation."
}