Files
Llama-3.2-3B-Instruct-GPTQ-…/quantize_config.json
ModelHub XC 0b8046e604 初始化项目,由ModelHub XC社区提供模型
Model: clowman/Llama-3.2-3B-Instruct-GPTQ-Int8
Source: Original Platform
2026-05-12 14:31:39 +08:00

21 lines
427 B
JSON

{
"bits": 8,
"group_size": 128,
"desc_act": true,
"sym": true,
"lm_head": false,
"quant_method": "gptq",
"checkpoint_format": "gptq",
"pack_dtype": "int32",
"meta": {
"quantizer": [
"gptqmodel:2.1.0"
],
"uri": "https://github.com/modelcloud/gptqmodel",
"damp_percent": 0.01,
"damp_auto_increment": 0.0025,
"static_groups": false,
"true_sequential": true,
"mse": 0.0
}
}