Al-Atlas-LLM is a 0.5B parameter language model specifically trained on Moroccan Darija, making it the first dedicated foundation model for Morocco’s primary spoken dialect. The model was trained on a carefully curated dataset of 155M tokens, focusing exclusively on authentic Moroccan Darija content. — Dedicated Darija Model: First language model trained specifically for Moroccan Arabic dialect — High-Quality Data: Curated dataset of 155M tokens from authentic Moroccan sources — Cultural Understanding: Captures nuanced cultural context and local expressions Our training corpus consists of 155M tokens of pure Moroccan Darija content, sourced from: — Social media conversations — Transcribed spoken content — Online forums and discussions — Local news and media — User-generat — Architecture: Transformer-based language model — Parameters: 0.5B — Context Window: 2048 tokens — Training Data: 155M tokens of pure Darija content — Chatbots for Moroccan users — Content generation in Darija — Text classification for…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: BounharAbdelaziz
Теги: qwen2, conversational, ar, ary, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 6
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
