This dataset contains the Supervised Fine-Tuning samples for Nile-Chat in both Arabic and Latin scripts. Each sample follows the following format:
[{"role": "user", "content": user_prompt}, {"role": "assistant", "content": assistant_answer}]
Dataset Categories