hanspeterlyngsoeraaschoujensen
/

deepseek-math-7b-instruct-awq-Q4

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

deepseek-math-7b-instruct-awq-Q4 / quant_config.json

hanspeterlyngsoeraaschoujensen's picture

hanspeterlyngsoeraaschoujensen

Upload quant_config.json with huggingface_hub

a3794cd verified 9 months ago

history blame contribute delete

126 Bytes

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