47 lines
1.1 KiB
JSON
47 lines
1.1 KiB
JSON
{
|
|
"bits": 4,
|
|
"group_size": 128,
|
|
"desc_act": false,
|
|
"lm_head": false,
|
|
"method": "gptq",
|
|
"quant_method": "gptq",
|
|
"format": "gptq",
|
|
"checkpoint_format": "gptq",
|
|
"pack_dtype": "int32",
|
|
"meta": {
|
|
"quantizer": [
|
|
"gptqmodel:7.1.0"
|
|
],
|
|
"uri": "https://github.com/modelcloud/gptqmodel",
|
|
"damp_percent": 0.1,
|
|
"damp_auto_increment": 0.01,
|
|
"static_groups": false,
|
|
"true_sequential": true,
|
|
"mse": 0.0,
|
|
"gptaq": null,
|
|
"foem": null,
|
|
"act_group_aware": true,
|
|
"fallback": {
|
|
"strategy": "rtn",
|
|
"threshold": "0.5%",
|
|
"smooth": null
|
|
},
|
|
"offload_to_disk": true,
|
|
"offload_to_disk_path": "/tmp/gptqmodel_pf205jdd",
|
|
"pack_impl": "cpu",
|
|
"gc_mode": "interval",
|
|
"wait_for_submodule_finalizers": false,
|
|
"auto_forward_data_parallel": true,
|
|
"dense_vram_strategy": "exclusive",
|
|
"dense_vram_strategy_devices": null,
|
|
"moe_vram_strategy": "exclusive",
|
|
"moe_vram_strategy_devices": null,
|
|
"mock_quantization": false,
|
|
"hessian": {
|
|
"chunk_size": null,
|
|
"chunk_bytes": null,
|
|
"staging_dtype": "float32"
|
|
}
|
|
},
|
|
"sym": true
|
|
} |