4bit/quantization_config.json

{
  "quantization_config": {
    "quant_method": "bitsandbytes",
    "_load_in_8bit": false,
    "_load_in_4bit": true,
    "llm_int8_threshold": 6.0,
    "llm_int8_skip_modules": null,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "load_in_4bit": true,
    "load_in_8bit": false
  },
  "quantization_method": "bitsandbytes",
  "bits": 4,
  "quant_type": "nf4"
}