llm-experiments / quantize_config.json

Elizaveta Kostenok

AutoGPTQ model: 4bits, 128gr default

ac88555 verified almost 2 years ago

266 Bytes

{
  "bits": 4,
  "group_size": 128,
  "damp_percent": 0.01,
  "desc_act": false,
  "static_groups": false,
  "sym": true,
  "true_sequential": true,
  "model_name_or_path": null,
  "model_file_base_name": null,
  "is_marlin_format": false,
  "quant_method": "gptq"
}

	{
	"bits": 4,
	"group_size": 128,
	"damp_percent": 0.01,
	"desc_act": false,
	"static_groups": false,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": null,
	"is_marlin_format": false,
	"quant_method": "gptq"
	}