File size: 1,085 Bytes
6ce1efe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
{
"bits": 4,
"group_size": 128,
"desc_act": false,
"lm_head": false,
"quant_method": "gptq",
"checkpoint_format": "gptq",
"pack_dtype": "int32",
"meta": {
"quantizer": [
"gptqmodel:5.7.0"
],
"uri": "https://github.com/modelcloud/gptqmodel",
"damp_percent": 0.05,
"damp_auto_increment": 0.01,
"static_groups": false,
"true_sequential": true,
"mse": 0.0,
"gptaq": null,
"act_group_aware": true,
"failsafe": {
"strategy": "rtn",
"threshold": "0.5%",
"smooth": {
"type": "mad",
"group_size_threshold": 128,
"k": 2.75
}
},
"offload_to_disk": true,
"offload_to_disk_path": "./gptqmodel_offload/hqdpgrum-rkaakpxx/",
"pack_impl": "cpu",
"mock_quantization": false,
"gc_mode": "interval",
"wait_for_submodule_finalizers": false,
"auto_forward_data_parallel": true,
"hessian": {
"chunk_size": null,
"chunk_bytes": null,
"staging_dtype": "float32"
},
"vram_strategy": "exclusive"
},
"sym": true,
"format": "gptq"
} |