How can I fine-tune a model for a downstream task?

TXH-mercury / VAST

Code and Model for VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

https://arxiv.org/abs/2305.18500

MIT License

241 stars 17 forks source link

Open echo233 opened 8 months ago

echo233 commented 8 months ago

I now need to validate the performance on the MSRVTT dataset. How can this be implemented? Could you provide a corresponding tutorial?

Fanzy27 commented 8 months ago

README.md