transformers

transformers copied to clipboard

add a test to match author's tokenization

1

# What does this PR do? I propose to add a test that aims to verify that we are able to reproduce the tokenization produced by the authors of MarkUpLM...

SaulLu

Added `num_channels` method for preprocessors and `num_query_channels` property for decoders.

esceptico

Fix attention mask handling in EoMT-DINOv3 converter

1

## Summary - update the conversion verifier to build an additive attention mask that mirrors the original EoMT implementation instead of multiplying by a boolean mask - seed PyTorch before...

NielsRogge

Add initial DEIMv2 model implementation

2

## Summary - bootstrap the DEIMv2 model package with configuration, modular/modeling code, and RT-DETR-derived image processors - add documentation stub and an RT-DETR-style test suite wired to the HGNetV2 backbone...

NielsRogge