Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published Dec 18, 2024 • 124
No More Adam: Learning Rate Scaling at Initialization is All You Need Paper • 2412.11768 • Published Dec 16, 2024 • 41
