localmodels
/

OpenAssistant-LLaMA-30B-SFT-7-GPTQ

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions

OpenAssistant-LLaMA-30B-SFT-7-GPTQ / quantize_config.json

ukim4's picture

Duplicate from localmodels/LLM

6a470d8 11 months ago

raw history blame

No virus

133 Bytes

	{
	"bits": 4,
	"group_size": -1,
	"damp_percent": 0.01,
	"desc_act": true,
	"sym": true,
	"true_sequential": true
	}