Hugging Face Blog·5d agoPruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem#llm#pruning#model-compressionAI research
Hugging Face Blog·18d agoSafety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic#ai-safety#alignment#model-behaviorAI safety & security
Hugging Face Blog·Aug 25, 2026Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original#4-bit#efficiency#model-compressionAI research