astronomer
/

Llama-3-8B-Instruct-GPTQ-4-Bit

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Llama-3-8B-Instruct-GPTQ-4-Bit / quantize_config.json

davidxmle's picture

Upload folder using huggingface_hub

ee9e2f9 verified about 1 month ago

raw history blame contribute delete

No virus

264 Bytes

	{
	"bits": 4,
	"group_size": 128,
	"damp_percent": 0.1,
	"desc_act": true,
	"static_groups": false,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": null,
	"is_marlin_format": false,
	"quant_method": "gptq"
	}