TheBloke
/

Wizard-Vicuna-13B-Uncensored-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

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

TheBloke's picture

Update for Transformers GPTQ support

d9b00ec over 1 year ago

92 Bytes

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