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

Gemma finetuning formatting #60

Open
mostafamdy opened this issue Apr 19, 2024 · 2 comments
Open

Gemma finetuning formatting #60

mostafamdy opened this issue Apr 19, 2024 · 2 comments
Assignees
Labels
type:support Support issues

Comments

@mostafamdy
Copy link

Hi,
I'm a bit confused. Should I use Gemma formatting tags during fine-tuning https://ai.google.dev/gemma/docs/formatting , or should I use this template: 'Instruction:\n{instruction}\n\nResponse:\n{response}' I found this template in many notebooks

@tilakrayal tilakrayal added type:support Support issues stat:awaiting response Status - Awaiting response from author and removed stat:awaiting response Status - Awaiting response from author labels Apr 24, 2024
@Gopi-Uppari Gopi-Uppari self-assigned this Sep 20, 2024
@Gopi-Uppari
Copy link
Collaborator

Hi @mostafamdy,

If you're working in an environment that supports or requires the Gemma format, it's best to follow the official documentation. The 'Instruction-Response' template, on the other hand, is commonly used for fine-tuning instruction-following models. You can also compare the outputs from both approaches and choose the one that produces the desired results.

Thank you.

@Gopi-Uppari
Copy link
Collaborator

Hi @mostafamdy,

Could you please confirm if this issue is resolved for you with the above comment ? Please feel free to close the issue if it is resolved ?

Thank you.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
type:support Support issues
Projects
None yet
Development

No branches or pull requests

3 participants