MENU

Fun & Interesting

Knowledge Distillation with Llama 3.1 405B | Llama for Developers

AI at Meta 4,058 lượt xem 3 months ago
Video Not Working? Fix It Now

Download Llama models ➡️ https://go.fb.me/kbpn54

In this video, Hamid and Suraj explore the use of large language models (LLMs) for fine-tuning and synthetic data generation. The discussion includes insights on the importance of fine-tuning for adapting pre-trained models to specific domains or tasks, and how LLMs can be used to generate synthetic data that can augment existing datasets and improve model performance.

### Timestamps
00:00 Intro
00:22 Importance of fine-tuning
02:01 Curation of datasets
03:43 Synthetic data
13:30 Risks of model collapse?
17:23 Distillation
20:39 Real world applications
26:08 Industry trends and small models

### Additional Resources
• Llama Trust & Safety Tools: https://go.fb.me/nnttf9
• Llama 3.1 announcement: https://go.fb.me/aqm9pc
• Llama 3.2 announcement: https://go.fb.me/53h2fe

- - -

Subscribe: https://www.youtube.com/aiatmeta?sub_confirmation=1
Learn more about our work: https://ai.meta.com

### Follow us on social media
Follow us on Twitter: https://twitter.com/aiatmeta/
Follow us on LinkedIn: https://www.linkedin.com/showcase/aiatmeta
Follow us on Threads: https://threads.net/aiatmeta
Follow us on Facebook: https://www.facebook.com/AIatMeta/

Comment