-
Approximating Two-Layer Feedforward Networks for Efficient Transformers
Paper • 2310.10837 • Published • 10 -
BitNet: Scaling 1-bit Transformers for Large Language Models
Paper • 2310.11453 • Published • 94 -
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
Paper • 2310.16795 • Published • 26 -
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Paper • 2310.16836 • Published • 10
Collections
Discover the best community collections!
Collections including paper arxiv:2402.02791