no flash_attn import to remove florence2languageforconditionalgeneration has generative capabilities, as prepare_inputs_for_generation is explicitly overwritten. however, it doesn't directly inherit from generationmixin.

[aiise117]

Hello! May I ask why this prompt message appears when loading the model for the first time. How should I set the shutdown prompt? Before, everything went smoothly and the speed of running this node was very fast. However, since I updated pytocr2.5cuida12.4, it takes a long time to load for the first time and there will be corresponding background prompts!
no flash_attn import to remove florence2languageforconditionalgeneration has generative capabilities, as prepare_inputs_for_generation is explicitly overwritten. however, it doesn't directly inherit from generationmixin. from 👉v4.50👈 onwards, pretrainedmodel will not inherit from generationmixin, and this model will lose the ability to call generate and other related functions. - if you're using trust_remote_code=true, you can get rid of this warning by loading the model with an auto class. see https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes - if you are the owner of the model architecture code, please modify your model class such that it inherits from generationmixin (after pretrainedmodel, otherwise you'll get an exception). - if you are not the owner of the model architecture class, please contact the model code owner to update it. a young woman, positioned directly in front of the camera, with her upper body facing the viewer, she has short, dark brown hair and brown eyes that are looking directly at the viewer with a warm smile on her face, her eyes are a deep brown color, and she is wearing a black sheer top, in the background, there is a cluttered desk with a computer and books, adding to the office setting, the woman's position is slightly off-center, creating a sense of intimacy and closeness, drawing the viewer's attention to her features offloading model...