Data Brew by Databricks
Welcome to Data Brew by Databricks with Denny and Brooke! In this series, we explore various topics in the data and AI community and interview subject matter experts in data engineering/data science. So join us with your morning brew in hand and get ready to dive deep into data + AI! For this first season, we will be focusing on lakehouses – combining the key features of data warehouses, such as ACID transactions, with the scalability of data lakes, directly against low-cost object stores.
Data Brew by Databricks
Reward Models | Data Brew | Episode 40
•
Databricks
•
Season 6
In this episode, Brandon Cui, Research Scientist at MosaicML and Databricks, dives into cutting-edge advancements in AI model optimization, focusing on Reward Models and Reinforcement Learning from Human Feedback (RLHF).
Highlights include:
- How synthetic data and RLHF enable fine-tuning models to generate preferred outcomes.
- Techniques like Policy Proximal Optimization (PPO) and Direct Preference
Optimization (DPO) for enhancing response quality.
- The role of reward models in improving coding, math, reasoning, and other NLP tasks.
Connect with Brandon Cui:
https://www.linkedin.com/in/bcui19/
