Day 2 Talks: JAX, Flax & Transformers 🤗

Day 2 Talks: JAX, Flax & Transformers 🤗 0:00:00 Suraj Patil & Patrick von Platen (Hugging Face): How to use JAX/Flax with Transformers 0:26:16 Sabrina J. Mielke (Johns Hopkins University & Hugging Face): From stateful code to purified JAX: how to build your neural net framework 1:01:35 Mostafa Dehghani (Google Brain): Long Range Arena: Benchmarking Efficient Transformers 1:28:05 Rohan Anil (Google Brain): Scalable Second Order Optimization for Deep Learning Find more information about the speakers and the talks here #thursday-july-1st