NourFakih
/

Vit-GPT2-COCO2017Flickr-85k-11

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Vit-GPT2-COCO2017Flickr-85k-11 / generation_config.json

NourFakih's picture

Training in progress, step 4500

f889465 verified 5 months ago

149 Bytes

	{
	"bos_token_id": 50256,
	"decoder_start_token_id": 50256,
	"eos_token_id": 50256,
	"pad_token_id": 50256,
	"transformers_version": "4.41.2"
	}