Skip to content

added smollama base model - 1B parameter #39543

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

dustinwloring1988
Copy link

@dustinwloring1988 dustinwloring1988 commented Jul 21, 2025

New base model added @ArthurZucker

smollama
-1B parameter model
-Modified llama architecture to use NoPE
-Tokoenizer from smollm3

smollama
-1B parameter model
- Modified llama architecture to use NoPE
- Tokoenizer from smollm3
Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

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

Thanks for the PR! Could you have a look into isolating the differences with Llama using modular: https://huggingface.co/docs/transformers/en/modular_transformers ! This will help a lot 🤗

TLDR write a modular_small_llama.py file that imports from llama4 or llama or other models that use NoPE, to isolate the diff then run python utils/modular_model_converter.py --files small_llama

@dustinwloring1988
Copy link
Author

@ArthurZucker yes no problem sorry did not see this until now.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants