返回到 Reinforcement Learning from Human Feedback
学生对 DeepLearning.AI 提供的 Reinforcement Learning from Human Feedback 的评价和反馈
31 个评分
课程概述
Large language models (LLMs) are trained on human-generated text, but additional methods are needed to align an LLM with human values and preferences.
Reinforcement Learning from Human Feedback (RLHF) is currently the main method for aligning LLMs with human values and preferences. RLHF is also used for further tuning a base LLM to align with values and preferences that are specific to your use case.
In this course, you will gain a conceptual understanding of the RLHF training process, and then practice applying RLHF to tune an LLM. You will:
1. Explore the two datasets that are used in RLHF training: the “preference” and “prompt” datasets.
2. Use the open source Google Cloud Pipeline Components Library, to fine-tune the Llama 2 model with RLHF.
3. Assess the tuned LLM against the original base model by comparing loss curves and using the “Side-by-Side (SxS)” method.
热门审阅
筛选依据：
1 - Reinforcement Learning from Human Feedback 的 6 个评论（共 6 个）
创建者 Ahmad A
•Jun 19, 2025
better to be expanded a bit, but overall, it is super course
创建者 Neil L
•Aug 17, 2025
Very nice overview about how RLHF works.
创建者 sajjad s
•May 14, 2025
great
创建者 Fady A S
•Dec 12, 2024
The content is amazing, the instructor is great and the flow is well structured. I did learn a lot, however, I wish the notebooks were structured so that I can write some of the code on my own as opposed to everything being ready and already verified working.
创建者 Manideep R E
•Jan 12, 2025
Overall worth a shot. Not in depth but good overview
创建者 Alessandro V
•Aug 28, 2024
andrew is always a guarantor