Nathan Lambert Releases RLHF Book on LLM Alignment and Post-Training
The new release pairs a print and free web book with a companion course, code, and model examples.
Entities: Nathan Lambert, Reinforcement Learning from Human Feedback
Nathan Lambert says his book *Reinforcement Learning from Human Feedback* is finished, pitching it as the resource he wanted when learning to fine-tune, align and post-train language models after ChatGPT. The project now lives at rlhfbook.com, where the site describes a free online book and course on RLHF and post-training. Lambert also linked a course page, Manning print edition and Amazon listing.
Combined views
58.3K
Reactions from ranked influencers
18 posts
@GregKamradt I'm still bringing you one later today!
This is a great book. Highly recommended.
My book, Reinforcement Learning from Human Feedback is done! This is the book I wish I had when learning to fine-tune, align, & now post-train models since ChatGPT. The resource has been built by me finding time to study and document the fundamentals on nights and weekends since 2024. Transferring as much of the intuitions of building Olmo as I possibly can in the book format. The book is launching with an over 10 hour, full course with slidedecks, functional code for the training chapters, an example model completions library, and of course the free online web version. Physical orders from Manning will ship in 1-2 weeks, and Amazon a week or so after. Thanks for your support!
My book, Reinforcement Learning from Human Feedback is done! This is the book I wish I had when learning to fine-tune, align, & now post-train models since ChatGPT. The resource has been built by me finding time to study and document the fundamentals on nights and weekends since 2024. Transferring as much of the intuitions of building Olmo as I possibly can in the book format. The book is launching with an over 10 hour, full course with slidedecks, functional code for the training chapters, an example model completions library, and of course the free online web version. Physical orders from Manning will ship in 1-2 weeks, and Amazon a week or so after. Thanks for your support!
@natolambert Amazing
@natolambert lets gooooo!!!!!! it is finally out 🙏
🥳 woohoo!
My book, Reinforcement Learning from Human Feedback is done! This is the book I wish I had when learning to fine-tune, align, & now post-train models since ChatGPT. The resource has been built by me finding time to study and document the fundamentals on nights and weekends since 2024. Transferring as much of the intuitions of building Olmo as I possibly can in the book format. The book is launching with an over 10 hour, full course with slidedecks, functional code for the training chapters, an example model completions library, and of course the free online web version. Physical orders from Manning will ship in 1-2 weeks, and Amazon a week or so after. Thanks for your support!