TheBloke
/

open-llama-3b-v2-wizard-evol-instuct-v2-196k-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

open-llama-3b-v2-wizard-evol-instuct-v2-196k-GPTQ / quantize_config.json

TheBloke's picture

GPTQ model commit

9291ae5 12 months ago

197 Bytes

	{
	"bits": [
	4
	],
	"group_size": [
	128
	],
	"damp_percent": [
	0.1
	],
	"desc_act": [
	true
	],
	"sym": true,
	"true_sequential": true
	}