Files
MagiSeek-Pro-V1-AutoRound-W…/quantization_config.json

11 lines
255 B
JSON
Raw Normal View History

{
"bits": 4,
"data_type": "int",
"group_size": 128,
"sym": true,
"low_gpu_mem_usage": true,
"autoround_version": "0.14.2",
"block_name_to_quantize": "model.layers",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq"
}