ssaroya
/

gptq_model

Inference Endpoints

Model card Files Files and versions Community

gptq_model / Wizard-Vicuna-13B-Uncensored-GPTQ /quantize_config.json

ssaroya's picture

Upload 10 files

ca84ecc over 1 year ago

history blame contribute delete

57 Bytes

	{
	"bits": 4,
	"desc_act": false,
	"group_size": 128
	}