AlexZigma
/

timesformer-bert-video-captioning

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

timesformer-bert-video-captioning / last-checkpoint /generation_config.json

AlexZigma's picture

Training in progress, step 2000

96e0f72 over 1 year ago

93 Bytes

	{
	"decoder_start_token_id": 101,
	"pad_token_id": 0,
	"transformers_version": "4.30.2"
	}