mistral-community
/

Mixtral-8x22B-v0.1-AWQ

Text Generation

4-bit precision

Mixture of Experts

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Mixtral-8x22B-v0.1-AWQ / quant_config.json

MaziyarPanahi's picture

Upload quant_config.json (#4)

5eac8ed verified 7 months ago

history blame contribute delete

82 Bytes

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