b8b5f14c45
Model: ModelCloud/Qwen1.5-1.8B-Chat-GPTQ-4bits-dynamic-cfg-with-lm_head-symTrue Source: Original Platform
36 lines
725 B
JSON
36 lines
725 B
JSON
{
|
|
"bits": 4,
|
|
"dynamic": {
|
|
"-:model\\.layers\\.([2-9]\\d*|[1-9]\\d+)\\..*": {},
|
|
".*\\.1\\..*": {
|
|
"bits": 8,
|
|
"desc_act": false,
|
|
"group_size": 32
|
|
},
|
|
"lm_head": {
|
|
"bits": 8,
|
|
"group_size": 32,
|
|
"sym": true,
|
|
"desc_act": false,
|
|
"mse": 2.4
|
|
}
|
|
},
|
|
"group_size": 128,
|
|
"desc_act": true,
|
|
"sym": true,
|
|
"lm_head": true,
|
|
"quant_method": "gptq",
|
|
"checkpoint_format": "gptq",
|
|
"pack_dtype": "int32",
|
|
"meta": {
|
|
"quantizer": [
|
|
"gptqmodel:1.8.0-dev"
|
|
],
|
|
"uri": "https://github.com/modelcloud/gptqmodel",
|
|
"damp_percent": 0.01,
|
|
"damp_auto_increment": 0.0025,
|
|
"static_groups": false,
|
|
"true_sequential": true,
|
|
"mse": 0.0
|
|
}
|
|
} |