casperhansen
/

mixtral-instruct-awq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

mixtral-instruct-awq / quant_config.json

casperhansen's picture

Upload folder using huggingface_hub

87dd4ec 11 months ago

history blame contribute delete

144 Bytes

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