TheBloke
/

Rogue-Rose-103b-v0.2-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Rogue-Rose-103b-v0.2-GPTQ / quantize_config.json

TheBloke's picture

GPTQ model commit

3b167e3 6 months ago

raw history blame

132 Bytes

	{
	"bits": 3,
	"group_size": -1,
	"damp_percent": 0.1,
	"desc_act": true,
	"sym": true,
	"true_sequential": true
	}