🤗 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.
Let's break Qwen-VL 🚨 (#42420)
* Lets braeaak! * pop attributes so we don't have 2 different values for the same key. Reported by TRL in the past * oh no, tying is messing up with slow tests.... * fix copies * migration guide
R
Raushan Turganbay committed
9bdec656c992617b4798589faa3f7c8bf21bb30a
Parent: e31c5f6
Committed by GitHub <[email protected]>
on 11/27/2025, 3:25:16 PM