TheBloke
/

Manticore-13B-Chat-Pyg-Guanaco-SuperHOT-8K-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Manticore-13B-Chat-Pyg-Guanaco-SuperHOT-8K-GPTQ / quantize_config.json

TheBloke's picture

Update for Transformers GPTQ support

bd3c66e about 1 year ago

158 Bytes

	{
	"bits": 4,
	"group_size": 128,
	"damp_percent": 0.01,
	"desc_act": false,
	"sym": true,
	"true_sequential": true,
	"model_file_base_name": "model"
	}