Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

Robust recipes to align language models with human and AI preferences

Longformer: The Long-Document Transformer

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Bi-Directional Attention Flow for Machine Comprehensions

Implementation of Reinforcement Algorithms from scratch

One-Shot Video Object Segmentation