rirv938
/

GPTQ-LLaMa-65B-4bit-triton

Text Generation

text-generation-inference

Model card Files Files and versions Community

GPTQ-LLaMa-65B-4bit-triton / quantize_config.json

robert

update

ea9369e about 1 year ago

raw history blame contribute delete

121 Bytes

	{
	"bits": 3,
	"group_size": -1,
	"damp_percent": 0.01,
	"desc_act": true,
	"sym": true,
	"true_sequential": true
	}