Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why Paper โข 2605.10889 โข Published May 11 โข 6
Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation Paper โข 2501.17433 โข Published Jan 29, 2025 โข 10
Running on CPU Upgrade 14k Open LLM Leaderboard ๐ 14k Track, rank and evaluate open LLMs and chatbots