add web demo/model to Huggingface
AK391 opened this issue · comments
Hi, would you be interested in adding CodeGen to Hugging Face? The Hub offers free hosting, and it would make your work more accessible and visible to the rest of the ML community. There is already a Salesforce organization on Huggingface: https://huggingface.co/Salesforce to add models/datasets/spaces(web demos) to.
Example from other organizations:
Keras: https://huggingface.co/keras-io
Microsoft: https://huggingface.co/microsoft
Facebook: https://huggingface.co/facebook
Example spaces with repos:
github: https://github.com/salesforce/BLIP
Spaces: https://huggingface.co/spaces/salesforce/BLIP
github: https://github.com/facebookresearch/omnivore
Spaces: https://huggingface.co/spaces/akhaliq/omnivore
and here are guides for adding spaces/models/datasets to your org
How to add a Space: https://huggingface.co/blog/gradio-spaces
how to add models: https://huggingface.co/docs/hub/adding-a-model
uploading a dataset: https://huggingface.co/docs/datasets/upload_dataset.html
Please let us know if you would be interested and if you have any questions, we can also help with the technical implementation.
Yes, definitely, thank you for the pointer. We are working on a HF integration with Leandro et al. as we speak
im interested in integration to HF
I have messed around with this and got it working, here are my unnoficial release:
@sallumandya1995 @AK391
https://huggingface.co/xhyi/CodeGen-350M-Multi
https://huggingface.co/xhyi/CodeGen-2B-Multi
@redthing1 can you add some example how to run for inference i.e. how to pass a query to the model?
@nashid It's ongoing; should be ready soon!: huggingface/transformers#17443
@nashid The pull request is merged. You could give it a try after installing transformers
from the repo directly.
You can find in the main branch here. It would take some time until this integration is included in a new release.
Gradio demo with HF now available:
https://huggingface.co/spaces/codeparrot/codegen-subspace
@enijkamp tried the URL. I am getting this error "500 Sorry, there is an error on our side.'
@nashid The gradio serving may have issues handling the load caused from recent tweets.
Here a colab demo on GPU:
https://colab.research.google.com/drive/11YU00W-JLNXn-3YckJGOSxFf_TQfCXYr#scrollTo=UUq-rqNGOa0L