🇲🇦 Building SILMA-Darija: Open LLMs for Moroccan Arabic & Arabizi

Automated excerpt

Most Arabic models struggle with Moroccan Darija. When you talk to them in Darija, they usually switch back to Gulf Arabic or formal Modern Standard Arabic (MSA), and they almost always break when people write in Arabizi using numbers (3, 7, 9). Moroccan Darija Dataset: 46,000+ cleaned Darija instruction and conversation pairs.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.