‘Vibe coding’ named Collins Dictionary’s Word of the Year

Vibe coding,” a form of software development that involves turning natural language into computer code by using artificial intelligence (AI), has been named Collins Dictionary’s Word of the Year for ...
GitHub

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Note: You may need 80GB GPU memory to run this script with deepseek-vl2-small and even larger for deepseek-vl2.
GitHub

Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

Samba is a simple yet powerful hybrid model with an unlimited context length. Its architecture is frustratingly simple: Samba = Mamba + MLP + Sliding Window Attention + MLP stacking at the layer level ...