marcsun13
/

Mixtral-tiny-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Mixtral-tiny-GPTQ / quantize_config.json

marcsun13's picture

marcsun13 HF staff

Duplicate from TheBlokeAI/Mixtral-tiny-GPTQ

3901bec 6 months ago

raw history blame contribute delete

No virus

186 Bytes

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