titanbot
/

gptj-6b-base-4bit-AWQ

Text Generation

Inference Endpoints

Model card Files Files and versions Community

gptj-6b-base-4bit-AWQ / quant_config.json

TitanML Co

Upload folder using huggingface_hub

cc19379 verified 8 months ago

history blame contribute delete

67 Bytes

	{
	"zero_point": true,
	"q_group_size": 128,
	"w_bit": 4
	}