solidrust
/

Xerxes-8B-Instruct-v0.4-AWQ

Text Generation

4-bit precision

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Xerxes-8B-Instruct-v0.4-AWQ / quant_config.json

first_name.last_name

adding quant config

75d271c 6 months ago

82 Bytes

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