🔱 Sailor2 Language Models Collection Sailing in South-East Asia with Inclusive Multilingual LLMs • 9 items • Updated Dec 3, 2024 • 22
💡 DICE Collection Self-alignment with DPO Implicit Rewards • 5 items • Updated Jul 28, 2024 • 9
RegMix: Data Mixture as Regression for Language Model Pre-training Paper • 2407.01492 • Published Jul 1, 2024 • 36
Bootstrapping Language Models with DPO Implicit Rewards Paper • 2406.09760 • Published Jun 14, 2024 • 39