OrionStarAI
/

Orion-14B-Chat-Int4

Text Generation

4-bit precision

Model card Files Files and versions Community

Orion-14B-Chat-Int4 / quant_config.json

DachengZhang's picture

init

9c7e7ed 4 months ago

raw history blame contribute delete

No virus

126 Bytes

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