EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation Paper • 2410.21271 • Published about 1 month ago • 6
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation Paper • 2410.21271 • Published about 1 month ago • 6
LLM-FP4: 4-Bit Floating-Point Quantized Transformers Paper • 2310.16836 • Published Oct 25, 2023 • 13
LLM-FP4: 4-Bit Floating-Point Quantized Transformers Paper • 2310.16836 • Published Oct 25, 2023 • 13
Oscillation-free Quantization for Low-bit Vision Transformers Paper • 2302.02210 • Published Feb 4, 2023 • 1