RLHF - Reinforcement Learning from Human Feedback скачать в хорошем качестве

RLHF - Reinforcement Learning from Human Feedback

This week we discuss Reinforcement Learning from Human Feedback (RLHF) a core technology used in the tuning the Large Language Models used in products such as ChatGPT and Bard. RLHF tunes the models in the products to be aligned with what humans expect for a response to a query. And it also insures the response is high quality and not toxic or unhelpful. In the video we watched a presentation from Deep Learning.AI describing their course on RLHF. As we watched the presentation, the group commented on their experience with RLHF and dove deeper into the techniques mentioned in the video. The end result was a great learning and sharing experience for everyone. Links Our Meetup: https://www.meetup.com/East-Bay-Tri-V... Video - Mastering RLHF with AWS: A Hands-on Workshop on Reinforcement Learning from Human Feedback : https://www.youtube.com/watch?v=-0pvr... Illustrated RLHF - https://huggingface.co/blog/rlhf PEFT -    • Parameter Efficient Fine-Tuning on Budget ...   Content 00:00 Introduction 02:49 Start of Mastering RLHF video 03:00 Generative AI project lifecycle 04:20 Generative model issues 12:00 Preparing dataset 13:48 Collecting human feedback 20:34 Fine tuning with RLHF 36:25 Issues with rewards 38:55 KL Divergence and PPO 43:46 Reducing Computation ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 😊About Us West Coast Machine Learning is a channel dedicated to exploring the exciting world of machine learning! Our group of techies is passionate about deep learning, neural networks, computer vision, tiny ML, and other cool geeky machine learning topics. We love to dive deep into the technical details and stay up to date with the latest research developments. Our Meetup group and YouTube channel is the perfect place to connect with other like-minded individuals who share your love of machine learning. We offer a mix of research paper discussions, coding reviews, and other data science topics. So, if you're looking to stay up to date with the latest developments in machine learning, connect with other techies, and learn something new, be sure to subscribe to our channel and join our Meetup community today! Meetup: https://www.meetup.com/east-bay-tri-v... ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ #machinelearning #ai #chatgpt #humanfeedback #artificalintellegence #rlhf #aitraining #mltraining #deeplearning.ai