Pedro H. V. Valois's picture

3 4

Pedro H. V. Valois

pvalois

·

https://phvv.me

Pedrexus

AI & ML interests

Interpretability

Recent Activity

upvoted a paper 29 days ago

Phi-4 Technical Report

authored a paper about 1 month ago

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

upvoted a paper about 1 month ago

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

View all activity

Organizations

None yet

pvalois's activity

commented 2 papers about 1 month 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 hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4 5 months ago

Running on multi-node infrastructure

#17 opened 5 months ago by

New activity in google/gemma-2-27b-it 5 months ago

Setting num_return_sequences results in shape mismatch error.

#28 opened 6 months ago by