TFMC
/

ELYZA-japanese-Llama-2-7b-instruct-GPTQ-4bit-64g

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

ELYZA-japanese-Llama-2-7b-instruct-GPTQ-4bit-64g / quantize_config.json

TFMC's picture

Upload 9 files

ed99bb0 over 1 year ago

186 Bytes

	{
	"bits": 4,
	"group_size": 64,
	"damp_percent": 0.01,
	"desc_act": true,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": "model"
	}