h2oai
/

h2ogpt-mixtral-8x7b-32k-awq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

h2ogpt-mixtral-8x7b-32k-awq / quant_config.json

arnocandel's picture

Initial commit.

284299b 10 months ago

144 Bytes

	{
	"zero_point": true,
	"q_group_size": 128,
	"w_bit": 4,
	"version": "GEMM",
	"modules_to_not_convert": [
	"gate"
	]
	}