quantization_config.json

{
  "_from_model_config": false,
  "llm_int8_enable_fp32_cpu_offload": false,
  "llm_int8_skip_modules": null,
  "llm_int8_threshold": 6.0,
  "load_in_8bit": true,
  "transformers_version": "4.28.0.dev0"
}