hiuman
/

Gemma-9B-IT-AWQ-Quantize

4-bit precision

Model card Files Files and versions

Gemma-9B-IT-AWQ-Quantize / quant_config.json

hiuman's picture

Upload folder using huggingface_hub

7f10b89 verified about 1 year ago

history blame contribute delete

90 Bytes

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