Pinned
Waking up to your favorite ML author replying to you? Feels like the universe just said, 'You're on the right path, kid.' 😌🔥
Pritam Reposted
Microsoft released LLM2CLIP: a CLIP model with longer context window for complex text inputs 🤯 TLDR; they replaced CLIP's text encoder with various LLMs fine-tuned on captioning, better top-k accuracy on retrieval 🔥 All models with Apache 2.0 license on @huggingface 😍
Pritam Reposted
In this video, I'll be deriving and coding Flash Attention from scratch. No prior knowledge of CUDA or Triton is required. Link to the video: youtu.be/zy8ChVd_oTM All the code will be written in Python with Triton, but no prior knowledge of Triton is required. I'll also…
United States Trends
- 1. $CUTO 7.986 posts
- 2. Northwestern 5.324 posts
- 3. Carnell Tate N/A
- 4. Denzel Burke N/A
- 5. Sheppard 2.589 posts
- 6. $CATEX N/A
- 7. Jeremiah Smith N/A
- 8. Arkansas 26,2 B posts
- 9. #collegegameday 5.017 posts
- 10. #Buckeyes N/A
- 11. Broden N/A
- 12. Ewers N/A
- 13. Wrigley 3.131 posts
- 14. Jim Knowles N/A
- 15. Jahdae Barron N/A
- 16. #Caturday 9.120 posts
- 17. Renji 6.190 posts
- 18. #HookEm 2.204 posts
- 19. DeFi 106 B posts
- 20. #SkoBuffs 2.642 posts
Loading...
Something went wrong.
Something went wrong.