Brind.
Concept

Pretraining.

Web pages
3,763
Websites
1,567
Connected ideas
598

Counted from our sample of 72 million web pages.

In Brind's news

Events and explainers that mention pretraining.

Brind's news hasn't mentioned pretraining recently. The web knows it well; the news doesn't. Its connections below are still worth a look.

Goes with

Ideas the web puts near pretraining most often, strongest first. Tap one to step into it.
  1. llm generated 1,111 sites
  2. gpu kernels 230 sites
  3. fine tuning 45,234 sites
  4. language models 35,996 sites
  5. post training 5,804 sites
  6. self supervised 2,014 sites
  7. pretrained 2,419 sites
  8. open source python 1,078 sites
  9. large language 40,162 sites
  10. python framework 971 sites
  11. contrastive 2,757 sites
  12. mixture of experts 1,443 sites
  13. finetuning 1,438 sites
  14. framework for large scale 203 sites
  15. language image 438 sites
  16. unearths 3,880 sites
  17. reinforcement learning 12,059 sites
  18. practical ai applications 532 sites
  19. sft 3,344 sites
  20. probabilistic model 920 sites
  21. pretrain 213 sites
  22. huggingface 2,341 sites
  23. marginal returns 503 sites
  24. probabilistic programming 358 sites
  25. context free grammars 353 sites
  26. systems with large 369 sites
  27. axolotl 2,560 sites
  28. project kick off meeting 299 sites
  29. vlm 1,447 sites
  30. vision language 2,180 sites

How this page is made. The connections are counted from how millions of web pages place ideas near each other, then cleaned up by simple rules. They show what people connect, not what is true. The events and explainers come from Brind's own pages.