EdysorEdutech
/

gatewaytrainedmodel

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

gatewaytrainedmodel / config.json

EdysorEdutech's picture

Create config.json

7b65987 verified 6 months ago

history blame contribute delete

125 Bytes

	{
	"model_type": "llama",
	"quantization_config": {
	"load_in_4bit": true,
	"bnb_4bit_compute_dtype": "float16"
	}
	}