How to finetune this model?
#1
by catastropiyush - opened
I wanted to start finetuning VLMs but I am not able to find a good resource for this. Can we finetune this on Google Colab's T4 GPU? How to manage different image sizes in the dataset? Thank you.
Yes, you can use T4 to train TexTeller, please refer to TexTeller’s GitHub repository for more details.
For images of different sizes in the dataset, they will be resized to 448 * 448 while maintaining the aspect ratio (the extra parts will be padded).