motheecreator
/

ViT-GPT2-Image_Captioning_model

vision-encoder-decoder

image-text-to-text

Generated from Trainer

image-captioning

Inference Endpoints

Model card Files Files and versions Community

ViT-GPT2-Image_Captioning_model / generation_config.json

motheecreator's picture

Upload ViT-GPT2 model

32e6478 verified about 2 months ago

89 Bytes

	{
	"bos_token_id": 50256,
	"eos_token_id": 50256,
	"transformers_version": "4.44.2"
	}