Skyler215
/

VIT_Captioning

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

VIT_Captioning / added_tokens.json

Skyler215's picture

End of training

4ac5dbc verified about 1 year ago

history blame contribute delete

83 Bytes

	{
	"<\|endoftext\|>": 50257,
	"[CLS]": 50258,
	"[PAD]": 50259,
	"[SEP]": 50260
	}