31 lines
714 B
JSON
31 lines
714 B
JSON
|
{
|
||
|
|
"bits": 4,
|
||
|
|
"group_size": 128,
|
||
|
|
"desc_act": false,
|
||
|
|
"sym": true,
|
||
|
|
"lm_head": false,
|
||
|
|
"quant_method": "gptq",
|
||
|
|
"checkpoint_format": "gptq",
|
||
|
|
"pack_dtype": "int32",
|
||
|
|
"meta": {
|
||
|
|
"quantizer": [
|
||
|
|
"gptqmodel:5.7.0-dev"
|
||
|
|
],
|
||
|
|
"uri": "https://github.com/modelcloud/gptqmodel",
|
||
|
|
"damp_percent": 0.01,
|
||
|
|
"damp_auto_increment": 0.01,
|
||
|
|
"static_groups": false,
|
||
|
|
"true_sequential": true,
|
||
|
|
"mse": 0.0,
|
||
|
|
"gptaq": false,
|
||
|
|
"gptaq_alpha": 0.25,
|
||
|
|
"act_group_aware": true,
|
||
|
|
"gc_mode": "on_stage_end",
|
||
|
|
"wait_for_submodule_finalizers": false,
|
||
|
|
"moe_bypass_router": true,
|
||
|
|
"auto_forward_data_parallel": true,
|
||
|
|
"failsafe": null
|
||
|
|
},
|
||
|
|
"pack_impl": "cpu",
|
||
|
|
"format": "gptq"
|
||
|
|
}
|