aoluo reposted
New LLM in town: ***phi-1 achieves 51% on HumanEval w. only 1.3B parameters & 7B tokens training dataset*** Any other >50% HumanEval model is >1000x bigger (e.g., WizardCoder from last week is 10x in model size and 100x in dataset size). How? ***Textbooks Are All You Need***
United States Trends
- 1. Broncos 59.6K posts
- 2. Bo Nix 16.5K posts
- 3. Geno 16.9K posts
- 4. $SMILEY 1,046 posts
- 5. Sean Payton 4,307 posts
- 6. #TNFonPrime 3,831 posts
- 7. YEONJUN 114K posts
- 8. Kenny Pickett 1,429 posts
- 9. Chip Kelly 1,802 posts
- 10. Jalen Green 5,943 posts
- 11. Bradley Beal 2,910 posts
- 12. Pete Carroll 1,643 posts
- 13. Jeanty 6,262 posts
- 14. Troy Franklin 2,350 posts
- 15. Thursday Night Football 6,255 posts
- 16. #criticalrolespoilers 3,668 posts
- 17. Daniel Carlson N/A
- 18. Ty Lue 1,280 posts
- 19. #NOLABELS_PART01 37.2K posts
- 20. Brock Bowers 4,810 posts
Loading...
Something went wrong.
Something went wrong.