Hugging Face's logo
Praxis Maldevide's picture

Praxis Maldevide

maldv
55 11 621
skyasher27's profile picture groceryheist's profile picture fibrosis's profile picture
·
https://www.maldevide.com/

AI & ML interests

ai alchemy

Recent Activity

liked a model 1 day ago
Qwen/Qwen2.5-32B
liked a model 1 day ago
meta-llama/Llama-3.1-70B
repliedto grimjim's post 2 days ago
I tinkered a bit with refusal ablation after seeing this article that proposed using optimal transport. https://arxiv.org/abs/2603.04355 Title: Efficient Refusal Ablation in LLM through Optimal Transport Authors: Geraldin Nanfack, Eugene Belilovsky, Elvis Dohmatob While closed Bures-Wasserstein sounded cool, the use of top-K at low K implied that the approach likely wouldn't capture refusal in detail, and increasing KL divergence with greater K suggested that the approach was too damaging for latent reasoning. I tried it out, and the results were disappointing.
View all activity

Organizations

Edgerunners's profile picture Hugging Face Discord Community's profile picture data3000's profile picture Anthracite Core's profile picture Anthracite's profile picture SillyTilly's profile picture