TheBloke
/

Yarn-Llama-2-7B-64K-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Yarn-Llama-2-7B-64K-GPTQ / quantize_config.json

TheBloke's picture

Initial GPTQ model commit

d5b8e5a about 1 year ago

187 Bytes

	{
	"bits": 4,
	"group_size": 128,
	"damp_percent": 0.1,
	"desc_act": false,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": "model"
	}