4bit
/

Llama-2-7b-Chat-GPTQ

Text Generation

Model card Files Files and versions Community

Llama-2-7b-Chat-GPTQ / quantize_config.json

camenduru's picture

thanks to meta-llama ❤ TheBloke ❤

2b31ea4 over 1 year ago

185 Bytes

	{
	"bits": 4,
	"group_size": 128,
	"damp_percent": 0.01,
	"desc_act": false,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": null
	}