Player FM 앱으로 오프라인으로 전환하세요!
Data synthesis for SOTA LLMs
Manage episode 399613971 series 2385063
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.
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:
- Karan Malhotra – LinkedIn
- Chris Benson – Twitter, GitHub, LinkedIn, Website
- Daniel Whitenack – Twitter, GitHub, Website
Show Notes:
Something missing or broken? PRs welcome!
챕터
1. Welcome to Practical AI (Dance Party!) (00:00:00)
2. Karan Malhotra (00:00:43)
3. Origins of Nous Research (00:01:57)
4. What is synthetic data (00:10:24)
5. Effects of model licensing (00:16:47)
6. Map of Nous (00:22:23)
7. How is Nous organized? (00:26:45)
8. Sponsor: Read Write Own (00:30:41)
9. Fine Tuning advice (00:31:48)
10. Stuff to look for (00:35:00)
11. What's next? (00:40:45)
12. Thank you! (00:45:03)
290 에피소드
Manage episode 399613971 series 2385063
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.
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:
- Karan Malhotra – LinkedIn
- Chris Benson – Twitter, GitHub, LinkedIn, Website
- Daniel Whitenack – Twitter, GitHub, Website
Show Notes:
Something missing or broken? PRs welcome!
챕터
1. Welcome to Practical AI (Dance Party!) (00:00:00)
2. Karan Malhotra (00:00:43)
3. Origins of Nous Research (00:01:57)
4. What is synthetic data (00:10:24)
5. Effects of model licensing (00:16:47)
6. Map of Nous (00:22:23)
7. How is Nous organized? (00:26:45)
8. Sponsor: Read Write Own (00:30:41)
9. Fine Tuning advice (00:31:48)
10. Stuff to look for (00:35:00)
11. What's next? (00:40:45)
12. Thank you! (00:45:03)
290 에피소드
모든 에피소드
×플레이어 FM에 오신것을 환영합니다!
플레이어 FM은 웹에서 고품질 팟캐스트를 검색하여 지금 바로 즐길 수 있도록 합니다. 최고의 팟캐스트 앱이며 Android, iPhone 및 웹에서도 작동합니다. 장치 간 구독 동기화를 위해 가입하세요.