Add EfficientNet (#21563)

* Add EfficientNet to transformers

docs/source/it/index.mdx

@@ -83,6 +83,7 @@ La libreria attualmente contiene implementazioni in JAX, PyTorch e TensorFlow, p
 1. **[DistilBERT](model_doc/distilbert)** (da HuggingFace), rilasciato assieme al paper [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://arxiv.org/abs/1910.01108) da Victor Sanh, Lysandre Debut e Thomas Wolf. La stessa tecnica è stata applicata per comprimere GPT2 in [DistilGPT2](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), RoBERTa in [DistilRoBERTa](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), Multilingual BERT in [DistilmBERT](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation) and a German version of DistilBERT.
 1. **[DPR](model_doc/dpr)** (da Facebook) rilasciato con il paper [Dense Passage Retrieval for Open-Domain Question Answering](https://arxiv.org/abs/2004.04906) da Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, e Wen-tau Yih.
 1. **[DPT](master/model_doc/dpt)** (da Intel Labs) rilasciato con il paper [Vision Transformers for Dense Prediction](https://arxiv.org/abs/2103.13413) da René Ranftl, Alexey Bochkovskiy, Vladlen Koltun.
+1. **[EfficientNet](model_doc/efficientnet)** (from Google Research) released with the paper [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946)  by Mingxing Tan and Quoc V. Le.
 1. **[EncoderDecoder](model_doc/encoder-decoder)** (da Google Research) rilasciato con il paper [Leveraging Pre-trained Checkpoints for Sequence Generation Tasks](https://arxiv.org/abs/1907.12461) da Sascha Rothe, Shashi Narayan, Aliaksei Severyn.
 1. **[ELECTRA](model_doc/electra)** (da Google Research/Stanford University) rilasciato con il paper [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://arxiv.org/abs/2003.10555) da Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning.
 1. **[FlauBERT](model_doc/flaubert)** (da CNRS) rilasciato con il paper [FlauBERT: Unsupervised Language Model Pre-training for French](https://arxiv.org/abs/1912.05372) da Hang Le, Loïc Vial, Jibril Frej, Vincent Segonne, Maximin Coavoux, Benjamin Lecouteux, Alexandre Allauzen, Benoît Crabbé, Laurent Besacier, Didier Schwab.