csdc-atl
/

Baichuan2-7B-Chat-GPTQ-Int4

Text Generation

4-bit precision

Model card Files Files and versions Community

Baichuan2-7B-Chat-GPTQ-Int4 / quantize_config.json

waterhorse1

damp_percent 0.1

2820e4b 9 months ago

raw history blame contribute delete

No virus

212 Bytes

	{
	"bits": 4,
	"group_size": 128,
	"damp_percent": 0.1,
	"desc_act": true,
	"static_groups": false,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": "model"
	}