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

Add SmolLM2 (WIP) #1848

Open
wants to merge 17 commits into
base: main
Choose a base branch
from
Open

Add SmolLM2 (WIP) #1848

wants to merge 17 commits into from

Conversation

ysjprojects
Copy link
Contributor

https://huggingface.co/collections/HuggingFaceTB/smollm2-6723884218bcda64b34d7db9

SOTA small language models (135M, 360M, 1.7B) by Hugging Face.

Great for on-device uses

Adding because of request on mobile-oriented models #1846

@Andrei-Aksionov
Copy link
Collaborator

Hello @ysjprojects

Do you think it's ready for a review or still in WIP?

@ysjprojects
Copy link
Contributor Author

Hello @ysjprojects

Do you think it's ready for a review or still in WIP?

just pushed some final changes, should be ready for review

@Andrei-Aksionov
Copy link
Collaborator

Andrei-Aksionov commented Dec 8, 2024

Hello @ysjprojects
I cannot download the model.
For some reason, huggingface_hub returns more files than are shown on the model page.
One of the files is training_args.bin, which breaks the download code.
In other words, the code finds .bin files and "thinks" that's this is a model, so doesn't make an attempt to download.safetensors.

(made a small change to download only model weights if there is .bin files.)

@ysjprojects
Copy link
Contributor Author

Hello @ysjprojects I cannot download the model. For some reason, huggingface_hub returns more files than are shown on the model page. One of the files is training_args.bin, which breaks the download code. In other words, the code finds .bin files and "thinks" that's this is a model, so doesn't make an attempt to download.safetensors.

(made a small change to download only model weights if there is .bin files.)

interesting, does the small change fix the issue or would I need to look into it?

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.

2 participants