Total runs:
14.9K
Run Growth:
7.5K
Growth Rate:
51.00%
Sponsored by
PoYo.AI
Omartificial-Intelligence-Space / Fanar-Math-R1-GRPO
Model's Last Updated: June 17 2025
text-generation
Introduction of Fanar-Math-R1-GRPO
Model Details of Fanar-Math-R1-GRPO
๐ง 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.
๐ Model Highlights
- ๐ Fine-tuned with GRPO , a sample-efficient reinforcement learning method
- ๐งฎ Specializes in multi-step mathematical reasoning
-
๐ฌ Outputs responses in a structured conversational format using
<think>and<answer>tags -
๐ง Trained using
TRL
(
transformers,peft, andmath_verify) - ๐ท๏ธ Useful for both instruction-following and math-heavy dialogue generation
๐ฆ Model Details
| Component | Description |
|---|---|
| Base Model |
QCRI/Fanar-1-9B-Instruct
|
| Fine-Tuning | GRPO via Hugging Face TRL |
| Dataset |
AI-MO/NuminaMath-TIR
|
| Format |
<think> ... </think> <answer> ... </answer>
tagged reasoning structure
|
| LoRA |
Enabled (modules:
q_proj
,
v_proj
, rank=8)
|
| Epochs | 1 (lightweight test configuration) |
| Tokenizer | Same as base model |
๐งช Inference Example
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 = '''ูู ู
ุฏููุฉ ูุจูุบ ุนุฏุฏ ุณูุงููุง 1 ู
ูููู ูุณู
ุฉุ ุฅุฐุง ูุงู 60% ู
ู ุงูุณูุงู ุจุงูุบููุ ู40% ู
ู ุงูุจุงูุบูู ูุนู
ูููุ ููู
ุนุฏุฏ ุงูุนุงู
ููู ูู ุงูู
ุฏููุฉุ'''
result, time_taken, tokens = generate_with_reasoning(prompt)
print(result)
๐ ๏ธ Training Setup
Configuration Summary
- learning_rate : 1e-5
- epochs : 1
- max_completion_length : 64
- num_generations : 4
- gradient_accumulation_steps : 16
- logging_steps : 10
Reward Functions
-
accuracy_reward
: validates correctness of the answer using
math_verify -
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
๐ Output Format
The model is trained to follow a reasoning-first format:
<think> ุฃููุงูุ ูุญุณุจ 60% ู
ู ู
ูููู ูุณู
ุฉุ ููู 600,000. ุซู
ูุญุณุจ 40% ู
ู ูุฐุง ุงูุนุฏุฏุ ููู 240,000. </think>
<answer> 240,000 </answer>
๐ฌ Citations
GRPO โ DeepSeekMath
@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
@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},
}
๐ Resources
Happy reasoning! ๐โจ
Runs of Omartificial-Intelligence-Space Fanar-Math-R1-GRPO on huggingface.co
15
Total runs
0
24-hour runs
1
3-day runs
3
7-day runs
14
30-day runs
More Information About Fanar-Math-R1-GRPO huggingface.co Model
Url of Fanar-Math-R1-GRPO
Fanar-Math-R1-GRPO huggingface.co Url
Provider of Fanar-Math-R1-GRPO huggingface.co
Other API from Omartificial-Intelligence-Space
Updated:September 07 2025
Total runs:
7.1K
Run Growth:
1.9K
Growth Rate:
27.17%
Total runs:
3.2K
Run Growth:
1.1K
Growth Rate:
35.23%
Total runs:
1.3K
Run Growth:
246
Growth Rate:
18.26%
Total runs:
1.1K
Run Growth:
935
Growth Rate:
82.96%
Total runs:
827
Run Growth:
41
Growth Rate:
4.96%
Total runs:
722
Run Growth:
366
Growth Rate:
50.69%
Total runs:
494
Run Growth:
13
Growth Rate:
2.63%
Total runs:
287
Run Growth:
189
Growth Rate:
65.85%
Total runs:
256
Run Growth:
0
Growth Rate:
0.00%
Total runs:
232
Run Growth:
76
Growth Rate:
32.76%
Total runs:
188
Run Growth:
188
Growth Rate:
100.00%
Total runs:
156
Run Growth:
143
Growth Rate:
91.67%
Total runs:
151
Run Growth:
97
Growth Rate:
64.24%
Total runs:
102
Run Growth:
12
Growth Rate:
11.76%
Total runs:
101
Run Growth:
8
Growth Rate:
7.92%
Total runs:
83
Run Growth:
19
Growth Rate:
22.89%
Total runs:
57
Run Growth:
57
Growth Rate:
100.00%
Total runs:
39
Run Growth:
14
Growth Rate:
35.90%
Total runs:
38
Run Growth:
35
Growth Rate:
92.11%
Total runs:
37
Run Growth:
37
Growth Rate:
100.00%
Total runs:
31
Run Growth:
7
Growth Rate:
22.58%
Total runs:
23
Run Growth:
-45
Growth Rate:
-195.65%
Total runs:
22
Run Growth:
10
Growth Rate:
45.45%
Total runs:
18
Run Growth:
10
Growth Rate:
55.56%
Total runs:
18
Run Growth:
11
Growth Rate:
61.11%
Total runs:
17
Run Growth:
7
Growth Rate:
41.18%
Total runs:
16
Run Growth:
-2
Growth Rate:
-12.50%
Total runs:
12
Run Growth:
10
Growth Rate:
83.33%
Total runs:
12
Run Growth:
0
Growth Rate:
0.00%
Total runs:
11
Run Growth:
7
Growth Rate:
63.64%
Total runs:
11
Run Growth:
0
Growth Rate:
0.00%
Total runs:
10
Run Growth:
3
Growth Rate:
30.00%
Total runs:
9
Run Growth:
1
Growth Rate:
11.11%
Total runs:
8
Run Growth:
1
Growth Rate:
12.50%
Total runs:
8
Run Growth:
1
Growth Rate:
12.50%
Total runs:
7
Run Growth:
0
Growth Rate:
0.00%
Total runs:
7
Run Growth:
-875
Growth Rate:
-12500.00%
Total runs:
6
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4
Run Growth:
-150
Growth Rate:
-3750.00%
Total runs:
4
Run Growth:
-7
Growth Rate:
-175.00%
Total runs:
3
Run Growth:
-2
Growth Rate:
-66.67%
Total runs:
2
Run Growth:
-3
Growth Rate:
-150.00%
Total runs:
2
Run Growth:
1
Growth Rate:
50.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%