Refusal in Language Models Is Mediated by a Single Direction
Paper • 2406.11717 • Published • 16
🏗️ Building on HF
Siddharth N.R
Siddh07ETH
AI & ML interests
AI Engineer | Large Language Models (LLMs) | Generative AI | Machine Learning | Open Source Researcher @pluto-AI-Labs
Recent Activity
liked a Space 1 day ago
Siddh07ETH/Hades-4B-Abliterated updated a Space 1 day ago
Siddh07ETH/Hades-4B-Abliterated published a Space 1 day ago
Siddh07ETH/Hades-4B-AbliteratedOrganizations
upvoted a paper 6 days ago
upvoted an article about 1 month ago
Article
llm-diff: Behavioral Regression Testing for Large Language Models
Siddh07ETH
• • 1 upvoted an article about 2 months ago
Article
The Distillation Research: Why 15,000 Clean Traces Outperform 100,000 Raw Ones
Siddh07ETH
• • 2 upvoted an article 2 months ago
Article
Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers
nvidia
• • 81