hugpadhugpad

Omartificial-Intelligence-Space / Fanar-Math-R1-GRPO

Text Generation313Updated Jun 17, 2025
Hugging Face

Downloads

31

Likes

3

Last updated

Jun 17, 2025

License

apache-2.0

Fanar-Math-R1-GRPO is a reasoning-optimized language model built on QCRI/Fanar-1-9B-Instruct. This version is fine-tuned using Group Relative Policy Optimization (GRPO) from the DeepSeekMath framework on the AI-MO/NuminaMath-TIR dataset. It is designed for step-by-step mathema…

Tasks & library

  • text generation
  • peft

Tags

  • peft
  • tensorboard
  • generated_from_trainer
  • trl
  • grpo
  • math

Technical specifications

ParametersNot available
Librarypeft
Languagesar, en
Base modelQCRI/Fanar-1-9B-Instruct
Licenseapache-2.0