Add a new AyaVision vision-language model family to the transformers library. The implementation must expose…

Add a new AyaVision vision-language model family to the transformers library. The implementation must expose…: a task in HF ML Tasksmith (Harbor dataset). Example pixel-shuffle output shape: input (B, 64, 32) with downsample factor=2 produces (B, 4, 4, 128) ; after the full projector with text…