Wezenite
/

gemma-2b-trader-8bit

Text Generation

8-bit precision

Model card Files Files and versions

gemma-2b-trader-8bit / quantization_config.json

Wezenite's picture

Upload folder using huggingface_hub

e3b5b8d verified about 2 months ago

history blame contribute delete

109 Bytes

	{
	"quantization_method": "bitsandbytes",
	"bits": 8,
	"load_in_8bit": true,
	"llm_int8_threshold": 6.0
	}