This chapter explores the advice and tips for fine-tuning models for specific tasks, including the importance of hyperparameters, training for more tokens and epochs, and the recommendation of the Axolotl library. They discuss various approaches and techniques in AI and machine learning, such as creating new instruction methodologies, merging models, and implementing techniques like DPO and reward models for censorship. They also touch on concepts like chain of thought, tree of thought, activation hacking, soft prompting, and the need for better sampling methods in AI.
Nous Research has been pumping out some of the best open access LLMs using SOTA data synthesis techniques. Their Hermes family of models is incredibly popular! In this episode, Karan from Nous talks about the origins of Nous as a distributed collective of LLM researchers. We also get into fine-tuning strategies and why data synthesis works so well.
Leave us a comment
Changelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
- Read Write Own – Read, Write, Own: Building the Next Era of the Internet—a new book from entrepreneur and investor Chris Dixon—explores one possible solution to the internet’s authenticity problem: Blockchains. From AI that tracks its source material to generative programs that compensate—rather than cannibalize—creators. It’s a call to action for a more open, transparent, and democratic internet. One that opens the black box of AI, tracks the origins we see online, and much more. Order your copy of Read, Write, Own today at readwriteown.com
- Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.
Featuring:
Show Notes:
Something missing or broken? PRs welcome!