A newer version of this model is available: unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit

Model Card for outputs

This model is a fine-tuned version of unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit. It has been trained using TRL.

Quick start



question = """ترجم النص التالي الي اللهجة الحجازية من فضلك يا بلال : انا اسمي لؤي عبد السلام أسكن في الاسكندرية بمصر مدينة الاسكندرية في مصر أدرس ذكاء اصطناعي"""

# Define a system prompt under prompt_style 
prompt_style = """Below is an instruction that describes a task, paired with an input that provides further context. 
Write a response that appropriately completes the request. 
Before answering, think carefully about the question and create a step-by-step chain of thoughts to ensure a logical and accurate response  .

### Instruction:
You are a arabic chatbot called belal with advanced knowledge in saudi arabia culture and can Speak different Saudi dialects. 
Please answer the following client question in arabic . 

### Question:
{}

### Response:
<think>{}"""

prompt = prompt_style.format(question, "")

....[Using the Model to predict]
<think>
أنا أفكر في السؤال اللي طرحته: ترجم، النص، التالي، الي، اللهجة، الحجازية، فضلك، يا، بلال، انا، اسمي، لؤي، عبد، السلام، أسكن، الاسكندرية، بمصر، مدينة، الاسكندرية، مصر، أدرس، ذكاء، اصطناعي 💭
ألاحظ أن الإجابة تحتوي على معلومات مرتبطة بالسؤال: ذكاء، مصر، اصطناعي، اسمي 👍.
أرى أن الإجابة أضافت بعض المعلومات مثل: في، عشان، لؤي، أبدي، عبد، أشتغل، أسكن، بلال، أسكندرية، لما 🤔.
لكن فيه كلمات ما ظهرت في الإجابة رغم وجودها في السؤال: لؤي، من، الفضلك، اسكن، اسمي، انا، التالي، اسمي، السلام، ترجم، أدرس، يا، اسكندرية، النص، بمصر، اللهجة، الحجازية، يا، بلال، مدينة، الاسكندرية، عبد، الفضل، التالي، لؤي، يصير، عبد، اصطناعي 🤨.
الإجابة ناقصة شوية مقارنة بالسؤال، يعني ممكن ما تكون كاملة 😕.
إذا قيمت التفكير المنطقي للإجابة، بتكون -11 من 5 نجوم 🌟.

وهذا هو منهجي في التفكير حول الحل 💡:
بدايةً، أفكر في السؤال وأحاول تحديد الكلمات المفتاحية اللي توضح المطلوب بالضبط 💭.
بعدها، أقارن الإجابة مع الكلمات المفتاحية لأشوف إذا كانت تفي بالغرض أو لا 🤔.
أحلل الإجابة بعناية وأشوف إذا كانت تضيف شيء مهم أو لا 🧐.
أفكر إذا كان فيه شيء مغفول عنه في الإجابة، يعني لو فيه تفاصيل أساسية غير موجودة 🤨.
وأخيرًا، أقيم تفاصيل الإجابة؛ هل هي واضحة وكافية؟ أم تحتاج تحسين؟ ✨

تقييم وضوح الإجابة: 🌟🌟🌟🌟🌟 (متوسط طول الكلمة: 4.36 أحرف).
تحليل تعقيد الإجابة: 19.00 (متوسط عدد الكلمات في الجملة)، يعني الإجابة معقدة 🧠.

فحص التحيز في الإجابة: لا يوجد تحيز واضح في الإجابة ✅. 🚨

✅ **تقرير التفكير بالكامل:**
تم التحليل بشكل كامل وشامل باستخدام المنهجيات المذكورة أعلاه. النقاط التي تم تقييمها هي:
🌟 وضوح الإجابة: 🌟🌟🌟🌟🌟
🌟 تعقيد الإجابة: معقدة
🌟 فحص التحيز: لا يوجد تحيز واضح في الإجابة ✅.
</think>
 اسمي لؤي عبد السلام، أبدي أسكن في أسكندرية، مصر. أشتغل عشان أدرس ذكاء اصطناعي. ><|end▁of▁sentence|>

Training procedure

Open In Colab

Visualize in Weights & Biases

This model was trained with SFT.

Framework versions

  • TRL: 0.14.0
  • Transformers: 4.43.4
  • Pytorch: 2.5.1+cu121
  • Datasets: 3.2.0
  • Tokenizers: 0.19.1

FOR BUSSINESS INQUIRE

CONTACT US : https://beetleware.com/

Citations

@loaiiabdalslam (Beetlware) @hamdy waleed (Beetlware)

Cite TRL as:


@misc {loai_abdalslam_2025,
    author       = { {loai abdalslam,hamdy waleed} },
    title        = { beetelware-saudi-R1-Distill-Llama-8B (Revision 03cfaf5) },
    year         = 2025,
    url          = { https://huggingface.co/loaiabdalslam/beetelware-saudi-R1-Distill-Llama-8B },
    doi          = { 10.57967/hf/4375 },
    publisher    = { Hugging Face }
}

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train loaiabdalslam/beetelware-saudi-R1-Distill-Llama-8B

Spaces using loaiabdalslam/beetelware-saudi-R1-Distill-Llama-8B 9