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

Warn if there if a chat template is provided by the model's tokenizer configuration and a caht_template is defined in the yaml #1120

Open
5 tasks done
winglian opened this issue Jan 14, 2024 · 1 comment
Labels
enhancement New feature or request good first issue Good for newcomers

Comments

@winglian
Copy link
Collaborator

⚠️ Please check that this feature request hasn't been suggested before.

  • I searched previous Ideas in Discussions didn't find any similar feature requests.
  • I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

There might be a mismatch between an existing chat template and a defined one.

✔️ Solution

Simply warn the user for now and continue

❓ Alternatives

No response

📝 Additional Context

No response

Acknowledgements

  • My issue title is concise, descriptive, and in title casing.
  • I have searched the existing issues to make sure this feature has not been requested yet.
  • I have provided enough information for the maintainers to understand and evaluate this request.
@winglian winglian added enhancement New feature or request good first issue Good for newcomers labels Jan 14, 2024
@Taytay
Copy link

Taytay commented Feb 3, 2024

@winglian : Is there a way to tell Axoltl to simply use the chat template of the tokenizer? I couldn't tell. I know that I can tell it what kind of format the dataset is in, but I didn't know how that affected the templating if the tokenizer has a different template defined.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request good first issue Good for newcomers
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants