quantization_info.json

{
  "model_name": "luca-deandrea/MNLP_M3_mcqa_model",
  "quantization_method": "bitsandbytes",
  "config_name": "bnb_4bit_nf4",
  "description": "4-bit NF4 with double quantization",
  "expected_compression": "~8x",
  "quantization_config": {
    "load_in_4bit": true,
    "load_in_8bit": false,
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "bnb_4bit_compute_dtype": "torch.bfloat16",
    "llm_int8_threshold": 6.0
  },
  "timestamp": "2025-06-10 21:31:13",
  "loading_time_seconds": 10.503286600112915,
  "memory_usage_gb": 0.5012297630310059,
  "test_generation": "Hello, I am a 16-year-old girl. I have"
}