nGPT: Normalized Transformer with Representation Learning on the Hypersphere Paper • 2410.01131 • Published Oct 1 • 8
Addition is All You Need for Energy-efficient Language Models Paper • 2410.00907 • Published Oct 1 • 143
Q-Sparse: All Large Language Models can be Fully Sparsely-Activated Paper • 2407.10969 • Published Jul 15 • 20
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark Paper • 2406.01574 • Published Jun 3 • 42
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality Paper • 2405.21060 • Published May 31 • 63
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits Paper • 2402.17764 • Published Feb 27 • 602
Think before you speak: Training Language Models With Pause Tokens Paper • 2310.02226 • Published Oct 3, 2023 • 2
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty Paper • 2401.15077 • Published Jan 26 • 18
SliceGPT: Compress Large Language Models by Deleting Rows and Columns Paper • 2401.15024 • Published Jan 26 • 68
