mesolitica
/

malaysian-llama2-7b-32k-instructions-AWQ

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

malaysian-llama2-7b-32k-instructions-AWQ / quant_config.json

huseinzol05's picture

Upload quant_config.json

1f98775 about 1 year ago

history blame contribute delete

90 Bytes

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