Intel
/

neural-chat-7b-v3-3-int4-inc

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

neural-chat-7b-v3-3-int4-inc / quantize_config.json

lvkaokao

update doc.

7011470 3 months ago

raw history blame contribute delete

No virus

254 Bytes

	{
	"bits": 4,
	"damp_percent": 0.01,
	"desc_act": false,
	"group_size": 128,
	"model_file_base_name": "model",
	"model_name_or_path": null,
	"quant_method": "intel/auto-round",
	"scale_dtype": "fp32",
	"sym": false,
	"true_sequential": false
	}