Maxime Labonne's picture

Maxime Labonne PRO

mlabonne

AI & ML interests

Post-training, model editing, quantization

Recent Activity

Organizations

Blog-explorers's profile picture Qwen's profile picture ZeroGPU Explorers's profile picture Merge Crew's profile picture Social Post Explorers's profile picture Liquid AI's profile picture gg-tt's profile picture rg-preview's profile picture

mlabonne's activity

commented on Uncensor any LLM with abliteration about 14 hours ago
view reply

Yes, in theory. In practice, it relies on whether the TransformerLens library supports DeepSeek or not. It'll also require an insane amount of VRAM.