TheBloke
/

h2ogpt-oasst1-512-30B-GPTQ

Text Generation

large language model

text-generation-inference

4-bit precision

Model card Files Files and versions Community

h2ogpt-oasst1-512-30B-GPTQ / quantize_config.json

TheBloke's picture

Update for Transformers GPTQ support

bcadd91 over 1 year ago

90 Bytes

	{
	"bits": 4,
	"desc_act": true,
	"group_size": -1,
	"model_file_base_name": "model"
	}