genta-tech
/

dukunlm-13b-awq-st

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

dukunlm-13b-awq-st / quant_config.json

farrelramdhani's picture

Duplicate from genta-tech/dukunlm-13b-awq

69d736c 12 months ago

history blame contribute delete

90 Bytes

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