Al-Khwarizmi

AI Math Tutor

زر huggingface.co ناقشه

متاحالذكاء الاصطناعي والإنتاجيةويب, iOS, Android, سطح المكتب, بوت / APIالعربية, الإنجليزية, لغات أخرى

معروض بلغة صاحب المنتج

ماذا يفعل

A small language model trained with full fine-tuning, LoRA, and DPO, to solve simple math problems, supports 9 languages and can easily be downloaded and used offline (1.9-6 GB variants). Training reached 87.21% mean token accuracy and cut validation loss by about 19%. Named after Muhammad ibn Musa al-Khwarizmi, the 9th-century mathematician whose name is the direct origin of the word "algorithm".

قصة البناء

كيف ساعد الذكاء الاصطناعي

أول نسخة تعمل

Around 2 weeks

من الفكرة إلى شيء يستخدمه الناس.

ما الذي فعله الذكاء الاصطناعي

Helped shape the training configurations I chose into code, translated an EN math dataset for multilingual training, helped draft the model card, and created the online demo.

ما الذي فعله الصانع

Chose the training methods and configurations for a number of iterations aimed at better results with step-by-step reasoning and more efficient local usage with smaller sizes.

أهم درس

“Small AI models can perform well while being usable locally when trained on a specific task or field.”