DeepInfra
/

pygmalion-13b-4bit-128g

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

pygmalion-13b-4bit-128g / quantize_config.json

Pernekhan's picture

Add quantize_config.json file to make it work with engines like vLLM

36f6209 11 months ago

history blame contribute delete

85 Bytes

	{
	"bits": 4,
	"desc_act": false,
	"group_size": 128,
	"true_sequential": true
	}