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

Adding Phi-4 multimodal #814

Open
haixuanTao opened this issue Mar 7, 2025 · 4 comments
Open

Adding Phi-4 multimodal #814

haixuanTao opened this issue Mar 7, 2025 · 4 comments
Assignees
Labels
good first issue Good for newcomers python Python API

Comments

@haixuanTao
Copy link
Collaborator

haixuanTao commented Mar 7, 2025

In order to improve audio performance, it could be good to add a dora-phi4 node that can read from audio, text and image by replicating nodes such as https://github.com/dora-rs/dora/blob/main/node-hub/dora-qwen2-5-vl

The model: https://huggingface.co/microsoft/Phi-4-multimodal-instruct

To get started on a new node, you can just:

dora new dora-phi4 --lang python --kind node
cd dora-phi4
uv pip install -e .
@haixuanTao haixuanTao added the good first issue Good for newcomers label Mar 7, 2025
@github-actions github-actions bot added the python Python API label Mar 7, 2025
@haixuanTao haixuanTao mentioned this issue Mar 7, 2025
2 tasks
@7SOMAY
Copy link
Contributor

7SOMAY commented Mar 7, 2025

Hi @haixuanTao, I guess command should be this : dora new dora-phi4 --lang python --kind node (instead of --type)

@haixuanTao
Copy link
Collaborator Author

Indeed sorry!

@7SOMAY
Copy link
Contributor

7SOMAY commented Mar 7, 2025

Please assign this issue to me.

@haixuanTao
Copy link
Collaborator Author

Done :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
good first issue Good for newcomers python Python API
Projects
None yet
Development

No branches or pull requests

2 participants