Hugging Face

Sparse Neural Networks (2/N): GPU Performance.

NVIDIA Ampere A100 introduces fine-grained structured…

A brief history of machine translation paradigms

Is the future of Neural Networks Sparse? An Introduction (1/N)

From principles to real-world library…

🦄🤝🦄 Encoder-decoders in Transformers: a hybrid pre-trained architecture for seq2seq

How To Write With Transformer

Neural Storytelling 1010101

Benchmarking Transformers: PyTorch and TensorFlow

🏎 Smaller, faster, cheaper, lighter: Introducing DilBERT, a distilled version of BERT

🌓 From TensorFlow to PyTorch

Friends and users of our open-source tools are often surprised how fast 🚀 we reimplement the latest SOTA…

Scaling a massive State-of-the-Art Deep Learning model in production