quantization_metadata.json

{
  "model_name": "allenai/Olmo-3-7B-Instruct",
  "quantization_format": "NVFP4",
  "calibration_samples": 2048,
  "original_memory_gb": "14.60",
  "quantized_memory_gb": "14.61",
  "memory_reduction_percent": "-0.1",
  "total_parameters_billions": "7.30",
  "target_device": "DGX Spark (GB10)",
  "export_path": "/workspace/quantized-output/Olmo-3-7B-NVFP4",
  "quantization_config": {
    "model_name": "allenai/Olmo-3-7B-Instruct",
    "quantization_format": "NVFP4",
    "calibration_samples": 2048,
    "calibration_max_length": 2048,
    "calibration_min_length": 100,
    "calibration_dataset": "allenai/c4",
    "calibration_dataset_config": "en",
    "calibration_dataset_split": "train",
    "target_device": "DGX Spark (GB10)",
    "hf_cache_dir": "~/.cache/huggingface",
    "output_dir": "./quantized-output/Olmo-3-7B-NVFP4",
    "log_dir": "./logs",
    "torch_dtype": "bfloat16",
    "device_map": "auto",
    "trust_remote_code": true
  },
  "created_at": "2025-11-22T04:10:03.593289"
}