Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Finetune #227

Merged
merged 17 commits into from
Feb 6, 2025
Merged

Finetune #227

merged 17 commits into from
Feb 6, 2025

Conversation

EthanReid
Copy link
Contributor

Example scripts to finetune the text and region model.

@forensicmike
Copy link

forensicmike commented Jan 27, 2025

This is fantastic @EthanReid thank you!!

One question, is it a problem that we are not calling model.text.train() somewhere?

2nd, should we possibly be using the config.tokenizer.templates instead of hard-coding? My thought process is that if we want to train on captioning, for example, fine-tuning with the \n\nQuestion:Describe this image.\n\nAnswer: doesn't seem to have much impact on the caption answers.

@vikhyat vikhyat merged commit 5dc35df into vikhyat:main Feb 6, 2025
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants