compressed-llm
/

vicuna-13b-v1.3-gptq

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

vicuna-13b-v1.3-gptq / quantize_config.json

danielz01's picture

Upload quantize_config.json with huggingface_hub

a6ded90 6 months ago

raw history blame

210 Bytes

	{
	"bits": 3,
	"group_size": 128,
	"damp_percent": 0.01,
	"desc_act": true,
	"static_groups": false,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": null
	}