numen-tech
/

EVA-D-Qwen2.5-1.5B-v0.0-GPTQ-Int4

Text Generation

4-bit precision

Model card Files Files and versions Community

EVA-D-Qwen2.5-1.5B-v0.0-GPTQ-Int4 / config.json

numen-tech's picture

Add weights

b591294 10 days ago

55 Bytes

	{
	"quantization_config": {
	"bits": 4
	}
	}