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

Removing the necessity of prompt details in data preparation #260

Merged
merged 14 commits into from
Nov 23, 2024

Conversation

shtoshni
Copy link
Collaborator

The current data preparation config requires prompt details to be specified.
However, there are times when we're dealing with data prepared for SFT, such as when we're downsampling the data.
This PR adds support for such cases.

Copy link
Collaborator

@wedu-nvidia wedu-nvidia left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we think here, we can add a warning (not error) that prompt_config and prompt_template are missing if they are not provided, can make it better if people might forget?

@shtoshni
Copy link
Collaborator Author

Do we think here, we can add a warning (not error) that prompt_config and prompt_template are missing if they are not provided, can make it better if people might forget?

Sure thing, let me add that!

@shtoshni
Copy link
Collaborator Author

Added the suggestions made and fixed tests. Let me know if anything else needs to be done.

Signed-off-by: Igor Gitman <[email protected]>
@Kipok Kipok merged commit 8993a67 into main Nov 23, 2024
3 checks passed
@shtoshni shtoshni deleted the shtoshni/data_prep_prompt branch November 26, 2024 17:57
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.

3 participants