Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models Paper • 2506.19697 • Published Jun 24 • 44
Outlier-Safe Pre-Training (OSP) Collection A collection of ablation and final models trained on the Outlier-Safe Pre-Training (OSP) framework. • 11 items • Updated Jun 26 • 3
Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information Paper • 2502.14258 • Published Feb 20 • 26
ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains Paper • 2410.09870 • Published Oct 13, 2024 • 8