From the source
The Hugging Face team improved TensorFlow models in Transformers (BERT, RoBERTa, ELECTRA, MPNet) for faster computation and added features for TensorFlow Serving deployment.
From the source
the Hugging Face team has been working hard on improving Transformers’ TensorFlow models to make them more robust and faster. The recent improvements are mainly focused on two aspects: Computational performance: BERT, RoBERTa, ELECTRA and MPNet have been improved in order to have a much faster computation time. This gain of computational performance is noticeable for all the computational aspects: graph/eager mode, TF Serving and for CPU/GPU/TPU devices. TensorFlow Serving: each of these TensorFlow model can be deployed with TensorFlow Serving to benefit of this gain of computational performance for inference.
huggingface.co
