macadeliccc
/

dolphin-2.8-experiment26-7b-awq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

dolphin-2.8-experiment26-7b-awq / quant_config.json

macadeliccc's picture

Add missing quant config JSON (#1)

ee6648f verified 10 months ago

history blame contribute delete

82 Bytes

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