Reinforcement Learning from Human Feedback
About this course
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.
75/100
CourseAsk score
- What the provider tells you
- 39/45
- Who stands behind it
- 20/35
- How complete the listing is
- 16/20
Scores how much the provider publishes and who stands behind it — not how well it is taught.
What you'll learn
- gain a conceptual understanding of RLHF
- practice applying RLHF to tune an LLM
- explore preference and prompt datasets used in RLHF training
- use the Google Cloud Pipeline Components Library for model fine-tuning
- assess a tuned model against the base model through loss curves
Course objectives
- understand how RLHF aligns LLMs with human values
- apply RLHF techniques to specific use cases
- utilize datasets and tools in RLHF training
Price shown by Coursera — confirm on their site.
Enroll on CourseraYou'll be redirected to Coursera to complete enrollment.
- Listed & compared by CourseAsk
- English · 0
Coursera
edX
Compared on these lists
Where this course ranks against the alternatives.