jamesdborin
/

opt-6.7b-4bit-AWQ

Text Generation

Model card Files Files and versions

opt-6.7b-4bit-AWQ / quant_config.json

Jamie@TitanML

Upload folder using huggingface_hub

1e98d02 over 2 years ago

history blame contribute delete

67 Bytes

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