Modelpublic

QuantTrio/KAT-Dev-GPTQ-Int4

sourceHugging Faceapache-2.0updated 11mo agoView on Hugging Face

1likes92downloads

quantize_config.json24 linesDownload Raw Back to root

1{2  "bits": 4,3  "group_size": 128,4  "desc_act": false,5  "sym": true,6  "lm_head": false,7  "quant_method": "gptq",8  "checkpoint_format": "gptq",9  "pack_dtype": "int32",10  "meta": {11    "quantizer": [12      "gptqmodel:4.2.5"13    ],14    "uri": "https://github.com/modelcloud/gptqmodel",15    "damp_percent": 0.05,16    "damp_auto_increment": 0.01,17    "static_groups": false,18    "true_sequential": true,19    "mse": 0.0,20    "v2": false,21    "v2_alpha": 0.25,22    "act_group_aware": false23  }24}