Pedro H. V. Valois's picture

4 7 1

Pedro H. V. Valois

pvalois

·

https://phvv.me

Pedrexus

AI & ML interests

Interpretability

Recent Activity

new activity 5 days ago

kernels-community/flash-attn3:Suport CUDA 12.8

upvoted an article 7 days ago

Enhance Your Models in 5 Minutes with the Hugging Face Kernel Hub

reacted to Jaward's post with 👍 about 2 months ago

finally, a course that makes diffusion math much easier to grasp, well done 👍 https://diffusion.csail.mit.edu/

View all activity

Organizations

None yet

New activity in kernels-community/flash-attn3 5 days ago

Suport CUDA 12.8

#1 opened 5 days ago by

commented 2 papers 7 months ago

Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation

Paper • 2412.07334 • Published Dec 10, 2024 • 16 •

Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation

Paper • 2412.07334 • Published Dec 10, 2024 • 16 •

New activity in google/gemma-2-27b-it 11 months ago

Setting num_return_sequences results in shape mismatch error.

#28 opened 12 months ago by