Qwen
/

Qwen-14B-Chat-Int8

Text Generation

8-bit precision

Model card Files Files and versions Community

Qwen-14B-Chat-Int8 / quantize_config.json

yangapku's picture

update int8 quantization info

4bf9d82 8 months ago

raw history blame contribute delete

No virus

214 Bytes

	{
	"bits": 8,
	"group_size": 128,
	"damp_percent": 0.01,
	"desc_act": false,
	"static_groups": false,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": "model"
	}