SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Add EfficientNet (#21563)

Browse Source 
* Add EfficientNet to transformers
This commit is contained in:
Alara Dirik
2023-02-20 16:37:11 +03:00
committed by GitHub
parent c9a0671477
commit 49ab16239c
34 changed files with 2176 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/source/es/index.mdx
View File

@@ -77,6 +77,7 @@ La biblioteca actualmente contiene implementaciones de JAX, PyTorch y TensorFlow
1. **[DistilBERT](model_doc/distilbert)** (de HuggingFace), publicado junto con el paper [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://arxiv.org/abs/1910.01108) por Victor Sanh, Lysandre Debut y Thomas Wolf. Se ha aplicado el mismo método para comprimir GPT2 en [DistilGPT2](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), RoBERTa en [DistilRoBERTa](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), BERT multilingüe en [DistilmBERT](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation) y una versión alemana de DistilBERT.
1. **[DPR](model_doc/dpr)** (de Facebook) publicado con el paper [Dense Passage Retrieval for Open-Domain Question Answering](https://arxiv.org/abs/2004.04906) por Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, y Wen-tau Yih.
1. **[DPT](master/model_doc/dpt)** (de Intel Labs) publicado con el paper [Vision Transformers for Dense Prediction](https://arxiv.org/abs/2103.13413) por 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)** (de Google Research) publicado con el paper [Leveraging Pre-trained Checkpoints for Sequence Generation Tasks](https://arxiv.org/abs/1907.12461) por Sascha Rothe, Shashi Narayan, Aliaksei Severyn.
1. **[ELECTRA](model_doc/electra)** (de Google Research/Universidad de Stanford) publicado con el paper [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://arxiv.org/abs/2003.10555) por Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning.
1. **[FlauBERT](model_doc/flaubert)** (de CNRS) publicado con el paper [FlauBERT: Unsupervised Language Model Pre-training for French](https://arxiv.org/abs/1912.05372) por Hang Le, Loïc Vial, Jibril Frej, Vincent Segonne, Maximin Coavoux, Benjamin Lecouteux, Alexandre Allauzen, Benoît Crabbé, Laurent Besacier, Didier Schwab.