numen-tech
/

FuseChat-Llama-3.1-8B-Instruct-w4a16g128asym

Text Generation

4-bit precision

Model card Files Files and versions Community

FuseChat-Llama-3.1-8B-Instruct-w4a16g128asym / config.json

numen-tech's picture

Add weights

b5c2707 6 months ago

history blame contribute delete

56 Bytes

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