🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Add optimized `PixtralImageProcessorFast` (#34836)
* Add optimized PixtralImageProcessorFast * make style * Add dummy_vision_object * Review comments * Format * Fix dummy * Format * np.ceil for math.ceil
M
Michael Goin committed
9d6f0ddcec215b24006c74acb7875fd2706a3a84
Parent: 6300212
Committed by GitHub <noreply@github.com>
on 11/28/2024, 3:04:05 PM