CM3- A Causal Masked Multimodal Model of the Internet

CM3- A Causal Masked Multimodal Model of the Internet

Yannic Kilcher via YouTube Direct link

- Why don't we use raw HTML?

13 of 14

13 of 14

- Why don't we use raw HTML?

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

CM3- A Causal Masked Multimodal Model of the Internet

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Intro & Overview
  2. 2 - Directly learning the structure of HTML
  3. 3 - Causally Masked Language Modelling
  4. 4 - A short look at how to use this model
  5. 5 - Start of interview
  6. 6 - Feeding language models with HTML
  7. 7 - How to get bi-directionality into decoder-only Transformers?
  8. 8 - Images are just tokens
  9. 9 - How does one train such giant models?
  10. 10 - CM3 results are amazing
  11. 11 - Large-scale dataset collection and content filtering
  12. 12 - More experimental results
  13. 13 - Why don't we use raw HTML?
  14. 14 - Does this paper contain too many things?

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.