Open LLM Upgrades 🆕 // Gemma 2 Performance 💎 // SeaKR's Self-aware Learning 🧠

HuggingFace has upgraded the Open LLM Leaderboard to v2, adding new benchmarks and improving the evaluation suite for easier reproducibility. Gemma 2, a new addition to the Gemma family of lightweight open models, delivers the best performance for its size and offers competitive alternatives to models that are 2-3× bigger. SeaKR is a new model that re-ranks retrieved knowledge based on the LLM's self-aware uncertainty, outperforming existing adaptive RAG methods in generating text with relevant and accurate information. Step-DPO is a new method that enhances the robustness and factuality of LLMs by learning from human feedback, achieving impressive results in long-chain mathematical reasoning. Contact:  [email protected] Timestamps: 00:34 Introduction 01:21 HuggingFace Updates Open LLM Leaderboard 03:19 Gemma 2: Improving Open Language Models at a Practical Size 04:16 From bare metal to a 70B model: infrastructure set-up and scripts 05:21 Fake sponsor 07:11 SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation 08:47 Simulating Classroom Education with LLM-Empowered Agents 10:16 Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs 12:31 Outro