Inference Deployment broken

I get this error when using the UI to deploy an inference endpoint: OSError: Error no file named diffusion_pytorch_model.bin found in directory /repository/unet for my model sdelargy/test-puppet-generation.

When I look in the unet folder I clearly see diffusion_pytorch_model.bin. What could be going on? I tried making the repo public but that didn’t fix the issue

Hi @sdelargy ! Thanks for reporting. We recommend setting the advanced parameter ‘framework’ to ‘Custom’, which will download all the files. If you would like to update the endpoint you can make this change via the API. If you’d like to do so in the UI, you’ll need to re-create the endpoint.

Hope this helps! Please let us know if you have additional questions.

1 Like

That worked, thanks so much!