PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation Paper • 2410.01680 • Published Oct 2 • 32
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models Paper • 2409.17481 • Published Sep 26 • 46
LLM Pruning and Distillation in Practice: The Minitron Approach Paper • 2408.11796 • Published Aug 21 • 55
Compact Language Models via Pruning and Knowledge Distillation Paper • 2407.14679 • Published Jul 19 • 38
RADIO Collection A collection of Foundation Vision Models that combine multiple models (CLIP, DINOv2, SAM, etc.). • 3 items • Updated Oct 1 • 5
Minitron Collection A family of compressed models obtained via pruning and knowledge distillation • 9 items • Updated Oct 3 • 59
