jamesdborin
/

gptj-6b-base-4bit-AWQ

Text Generation

Inference Endpoints

Model card Files Files and versions Community

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

Jamie@TitanML

Upload folder using huggingface_hub

9c8c6fc about 1 year ago

history blame contribute delete

67 Bytes

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