kuleshov
/

llama-30b-4bit

Text Generation

Inference Endpoints

Model card Files Files and versions Community

llama-30b-4bit / quant_config.json

kuleshov's picture

first commit

22e0024 over 1 year ago

176 Bytes

	{
	"dataset": "c4",
	"bits": 4,
	"nsamples": 128,
	"groupsize": 64,
	"act_order": true,
	"percdamp": 0.01,
	"seed": 0,
	"nearest": false,
	"save": "./llama-30b-4bit"
	}