gpt2-AutoRound-W4A16-RTN / quantization_config.json

Upload quantized model gpt2-AutoRound-W4A16-RTN

a6c7887 verified 5 months ago

214 Bytes

{
  "bits": 4,
  "data_type": "int",
  "group_size": 128,
  "sym": true,
  "iters": 0,
  "seqlen": 1024,
  "autoround_version": "0.12.3",
  "quant_method": "auto-round",
  "packing_format": "auto_round:auto_gptq"
}

	{
	"bits": 4,
	"data_type": "int",
	"group_size": 128,
	"sym": true,
	"iters": 0,
	"seqlen": 1024,
	"autoround_version": "0.12.3",
	"quant_method": "auto-round",
	"packing_format": "auto_round:auto_gptq"
	}