espressor
/

google.gemma-2b-it_W8A8_int8

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

compressed-tensors

Model card Files Files and versions Community

google.gemma-2b-it_W8A8_int8 / generation_config.json

xzyao's picture

Upload folder using huggingface_hub

3443876 verified 14 days ago

history blame contribute delete

132 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 2,
	"eos_token_id": 1,
	"pad_token_id": 0,
	"transformers_version": "4.46.3"
	}