jphme
/

em_german_7b_v01_gptq

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

em_german_7b_v01_gptq / quantize_config.json

jphme's picture

upload gptq

2fb9042 8 months ago

raw history blame contribute delete

No virus

152 Bytes

	{
	"bits": 4,
	"damp_percent": 0.1,
	"desc_act": 1,
	"group_size": 32,
	"sym": true,
	"true_sequential": true,
	"model_file_base_name": "model"
	}