NourFakih
/

image-captioning-Vit-GPT2-Flickr8k

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

image-captioning-Vit-GPT2-Flickr8k / generation_config.json

NourFakih's picture

Model save

cc5d1dd verified 9 months ago

149 Bytes

	{
	"bos_token_id": 50256,
	"decoder_start_token_id": 50256,
	"eos_token_id": 50256,
	"pad_token_id": 50256,
	"transformers_version": "4.39.3"
	}