Machine Learning

🚧 Simple considerations for simple people building fancy neural networks

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

NVIDIA Ampere A100 introduces fine-grained structured…

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

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

🌻The Best and Most Current of Modern Natural Language Processing

Introducing FastBert — A simple Deep Learning library for BERT Models

A simple to use Deep Learning…