-
One Wide Feedforward is All You Need
Paper • 2309.01826 • Published • 31 -
Gated recurrent neural networks discover attention
Paper • 2309.01775 • Published • 6 -
FLM-101B: An Open LLM and How to Train It with $100K Budget
Paper • 2309.03852 • Published • 42 -
Large Language Models as Optimizers
Paper • 2309.03409 • Published • 72
Collections
Discover the best community collections!
Collections including paper arxiv:2309.03409
-
MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
Paper • 2309.04662 • Published • 21 -
Neurons in Large Language Models: Dead, N-gram, Positional
Paper • 2309.04827 • Published • 16 -
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
Paper • 2309.05516 • Published • 8 -
DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs
Paper • 2309.03907 • Published • 6
-
Large Language Models as Optimizers
Paper • 2309.03409 • Published • 72 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 102 -
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework
Paper • 2404.14619 • Published • 122 -
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Paper • 2404.14219 • Published • 239