🤗 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.
🚨Fix floating-point precision in JanusImageProcessor resize (#43187)
* Fix floating-point precision in JanusImageProcessor resize * Regenerate image_processing_janus.py from modular file * Fix int() truncation in deepseek_vl and janus_fast * fix-repo * fix integration tests --------- Co-authored-by: yonigozlan <[email protected]> Co-authored-by: Yoni Gozlan <[email protected]>
M
Murat Raimbekov committed
56c4b5e37f92b4ee8716beca3b26dee5c5e63dc5
Parent: 78e4f88
Committed by GitHub <[email protected]>
on 2/2/2026, 6:47:33 PM