Abdou
/

vit-swin-base-224-gpt2-image-captioning

vision-encoder-decoder

image-text-to-text

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

vit-swin-base-224-gpt2-image-captioning / generation_config.json

Abdou's picture

End of training

8eb50e4 about 2 years ago

179 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 50256,
	"decoder_start_token_id": 50256,
	"eos_token_id": 50256,
	"pad_token_id": 50256,
	"transformers_version": "4.26.0"
	}