casperhansen
/

mpt-7b-8k-chat-awq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

mpt-7b-8k-chat-awq / quant_config.json

casperhansen's picture

Update quant_config.json

6c68c97 about 1 year ago

90 Bytes

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