AIFunOver
/

gemma-2-2b-it-openvino-8bit

Text Generation

8-bit precision

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

gemma-2-2b-it-openvino-8bit / generation_config.json

AIFunOver's picture

Upload generation_config.json with huggingface_hub

457f78e verified 3 months ago

151 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 2,
	"eos_token_id": [
	1,
	107
	],
	"pad_token_id": 0,
	"transformers_version": "4.45.2"
	}