Skip to content

[Hint] AutoProcessor with use_fast=False #68

Description

@mikemoik

with current torch versions and pyhton 3.14 i had to add the option

processor = AutoProcessor.from_pretrained(MODEL_NAME, use_fast=False)

as the hint already suggested.
without it i got:

  File "/topath/lib/python3.14/site-packages/torch/nn/functional.py", line 4924, in interpolate
    raise NotImplementedError(
    ...<3 lines>...
    )
NotImplementedError: Input Error: Only 3D, 4D and 5D input Tensors supported (got 4D) for the modes: nearest | linear | bilinear | bicubic | trilinear | area | nearest-exact (got lanczos)

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions