Leandro Von Werra

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

FineWeb2: One Pipeline to Scale Them All — Adapting Pre-Training Data Processing to Every Language

SmolLM2: When Smol Goes Big — Data-Centric Training of a Fully Open Small Language Model

SmolVLM: Redefining small and efficient multimodal models