CoolFace
Modelpublic

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

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
3likes10downloads
Model Card

๐Ÿง  Fanar-Math-R1-GRPO

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 mathematical problem-solving with structured reasoning in both English and Arabic.

image/png

๐Ÿš€ Model Highlights

  • โ€”๐Ÿ” Fine-tuned with GRPO, a sample-efficient reinforcement learning method
  • โ€”๐Ÿงฎ Specializes in multi-step mathematical reasoning
  • โ€”๐Ÿ’ฌ Outputs responses in a structured conversational format using <think> and <answer> tags
  • โ€”๐Ÿง  Trained using TRL (transformers, peft, and math_verify)
  • โ€”๐Ÿท๏ธ Useful for both instruction-following and math-heavy dialogue generation

๐Ÿ“ฆ Model Details

ComponentDescription
Base Model`QCRI/Fanar-1-9B-Instruct`
Fine-TuningGRPO via Hugging Face TRL
Dataset`AI-MO/NuminaMath-TIR`
Format<think> ... </think> <answer> ... </answer> tagged reasoning structure
LoRAEnabled (modules: q_proj, v_proj, rank=8)
Epochs1 (lightweight test configuration)
TokenizerSame as base model

๐Ÿงช Inference Example

python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import time

model_id = "Omartificial-Intelligence-Space/Fanar-Math-R1-GRPO"
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)

def generate_with_reasoning(prompt_text):
    inputs = tokenizer(prompt_text, return_tensors="pt").to(model.device)
    start = time.time()
    with torch.no_grad():
        output = model.generate(**inputs, max_length=1024)
    end = time.time()

    generated = tokenizer.decode(output[0], skip_special_tokens=True)
    duration = end - start
    num_input_tokens = inputs["input_ids"].shape[1]
    num_generated_tokens = output.shape[1] - num_input_tokens

    return generated, duration, num_generated_tokens

# Example Arabic math problem
prompt_text = '''ููŠ ู…ุฏูŠู†ุฉ ูŠุจู„ุบ ุนุฏุฏ ุณูƒุงู†ู‡ุง 1 ู…ู„ูŠูˆู† ู†ุณู…ุฉุŒ ุฅุฐุง ูƒุงู† 60% ู…ู† ุงู„ุณูƒุงู† ุจุงู„ุบูŠู†ุŒ ูˆ40% ู…ู† ุงู„ุจุงู„ุบูŠู† ูŠุนู…ู„ูˆู†ุŒ ููƒู… ุนุฏุฏ ุงู„ุนุงู…ู„ูŠู† ููŠ ุงู„ู…ุฏูŠู†ุฉุŸ'''

result, time_taken, tokens = generate_with_reasoning(prompt)
print(result)

๐Ÿ› ๏ธ Training Setup

Configuration Summary

  • โ€”learning_rate: 1e-5
  • โ€”epochs: 1
  • โ€”max_completion_length: 64
  • โ€”num_generations: 4
  • โ€”gradient_accumulation_steps: 16
  • โ€”logging_steps: 10

Reward Functions

  • โ€”accuracy_reward: validates correctness of the answer using math_verify
  • โ€”format_reward: checks for proper usage of <think> and <answer> tags

Libraries & Versions

transformers==4.47.1
trl==0.14.0
peft==0.14.0
datasets==2.21.0
math_verify==0.3.3
torch==2.4.1

๐Ÿ“š Output Format

The model is trained to follow a reasoning-first format:

<think> ุฃูˆู„ุงู‹ุŒ ู†ุญุณุจ 60% ู…ู† ู…ู„ูŠูˆู† ู†ุณู…ุฉุŒ ูˆู‡ูˆ 600,000. ุซู… ู†ุญุณุจ 40% ู…ู† ู‡ุฐุง ุงู„ุนุฏุฏุŒ ูˆู‡ูˆ 240,000. </think>
<answer> 240,000 </answer>

๐Ÿ”ฌ Citations

GRPO โ€“ DeepSeekMath

bibtex
@article{zhihong2024deepseekmath,
  title={DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models},
  author={Shao, Zhihong and Wang, Peiyi and Zhu, Qihao and Xu, Runxin and Song, Junxiao and Zhang, Mingchuan and Li, Y.K. and Wu, Y. and Guo, Daya},
  journal={arXiv preprint arXiv:2402.03300},
  year={2024}
}

TRL Library

bibtex
@misc{vonwerra2022trl,
  title={TRL: Transformer Reinforcement Learning},
  author={von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouรฉdec, Quentin},
  year={2022},
  howpublished={\url{https://github.com/huggingface/trl}}
}
@misc{fanarllm2025,
      title={Fanar: An Arabic-Centric Multimodal Generative AI Platform}, 
      author={Fanar Team and Ummar Abbas and Mohammad Shahmeer Ahmad and Firoj Alam and Enes Altinisik and Ehsannedin Asgari and Yazan Boshmaf and Sabri Boughorbel and Sanjay Chawla and Shammur Chowdhury and Fahim Dalvi and Kareem Darwish and Nadir Durrani and Mohamed Elfeky and Ahmed Elmagarmid and Mohamed Eltabakh and Masoomali Fatehkia and Anastasios Fragkopoulos and Maram Hasanain and Majd Hawasly and Mus'ab Husaini and Soon-Gyo Jung and Ji Kim Lucas and Walid Magdy and Safa Messaoud and Abubakr Mohamed and Tasnim Mohiuddin and Basel Mousi and Hamdy Mubarak and Ahmad Musleh and Zan Naeem and Mourad Ouzzani and Dorde Popovic and Amin Sadeghi and Husrev Taha Sencar and Mohammed Shinoy and Omar Sinan and Yifan Zhang and Ahmed Ali and Yassine El Kheir and Xiaosong Ma and Chaoyi Ruan}},
      year={2025},
      url={https://arxiv.org/abs/2501.13944}, 
}

๐Ÿ”— Resources

Happy reasoning! ๐Ÿ”โœจ