Collection by
Jun 24, 2024
Jun 24, 2024
-
Approximating Two-Layer Feedforward Networks for Efficient Transformers
Paper • 2310.10837 • Published • 11 -
BitNet: Scaling 1-bit Transformers for Large Language Models
Paper • 2310.11453 • Published • 96 -
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
Paper • 2310.16795 • Published • 27 -
LLM-FP4: 4-Bit Floating-Point Quantized Transformers
Paper • 2310.16836 • Published • 14