keyfan
/

Qwen-72B-Chat-2bit

Text Generation

Model card Files Files and versions Community

Qwen-72B-Chat-2bit / quantization_config.json

keyfan's picture

Upload folder using huggingface_hub (#1)

fdd3211 5 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"quant_method": "QUiP",
	"rescale_WH": false,
	"use_rand": true,
	"codebook": "E8P12",
	"codesz": 8,
	"idx_dtype": "torch.int16",
	"merge_suv": true,
	"modules_to_not_convert": null
	}