|
|
---
|
|
|
license: apache-2.0
|
|
|
base_model: Qwen/Qwen3-8B
|
|
|
datasets:
|
|
|
- batuhanozkose/Rehber-CoT-Science
|
|
|
tags:
|
|
|
- fine-tuned
|
|
|
- science
|
|
|
- turkish
|
|
|
- qwen3
|
|
|
- academic
|
|
|
- chain-of-thought
|
|
|
- reasoning
|
|
|
- stem
|
|
|
language:
|
|
|
- tr
|
|
|
- en
|
|
|
pipeline_tag: text-generation
|
|
|
model-index:
|
|
|
- name: Rehber-Science
|
|
|
results: []
|
|
|
---
|
|
|
|
|
|
# 🎓 Rehber-Science
|
|
|
|
|
|
<div align="center">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
**Türkçe bilimsel soru-cevap ve Chain-of-Thought muhakeme için fine-tune edilmiş Qwen3-8B modeli**
|
|
|
|
|
|
*Adım adım düşünme, matematiksel çözümleme ve Python doğrulama kodu üretimi*
|
|
|
|
|
|
[Model](https://huggingface.co/batuhanozkose/Rehber-Science) • [Dataset](https://huggingface.co/datasets/batuhanozkose/Rehber-CoT-Science) • [Author](https://huggingface.co/batuhanozkose)
|
|
|
|
|
|
</div>
|
|
|
|
|
|
---
|
|
|
|
|
|
## 📌 Changelog
|
|
|
|
|
|
| Version | Date | Changes |
|
|
|
|---------|------|---------|
|
|
|
| **v2.0** | 24.12.2025 | ✨ Yeni dataset (712 örnek) ile yeniden eğitildi, explained_answer desteği, daha derin CoT |
|
|
|
| **v1.0** | 15.12.2025 | 🚀 İlk sürüm: 500+ örnek ile full fine-tuning |
|
|
|
|
|
|
---
|
|
|
|
|
|
## 🎯 Overview
|
|
|
|
|
|
**Rehber-Science** is a Turkish scientific reasoning model based on Qwen3-8B, fine-tuned on the [Rehber-CoT-Science](https://huggingface.co/datasets/batuhanozkose/Rehber-CoT-Science) dataset. The model excels at:
|
|
|
|
|
|
- 🧠 **Chain-of-Thought Reasoning**: Step-by-step problem solving
|
|
|
- 🔬 **Scientific Domains**: Physics, Chemistry, Biology, Mathematics, Statistics, Engineering
|
|
|
- 🐍 **Code Generation**: Executable Python verification code
|
|
|
- 📝 **Detailed Explanations**: Real-world intuitive explanations
|
|
|
- 🇹🇷 **Turkish Language**: Academic Turkish with proper scientific terminology
|
|
|
|
|
|
---
|
|
|
|
|
|
## 📊 Model Details
|
|
|
|
|
|
| Property | Value |
|
|
|
|----------|-------|
|
|
|
| **Base Model** | [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) |
|
|
|
| **Parameters** | 8B |
|
|
|
| **Training Type** | Full Fine-Tuning |
|
|
|
| **Dataset** | [batuhanozkose/Rehber-CoT-Science](https://huggingface.co/datasets/batuhanozkose/Rehber-CoT-Science) |
|
|
|
| **Dataset Size** | 712 samples |
|
|
|
| **Language** | Turkish 🇹🇷 |
|
|
|
| **Context Length** | 32K tokens |
|
|
|
| **Precision** | bfloat16 |
|
|
|
|
|
|
### Training Infrastructure
|
|
|
|
|
|
| Component | Details |
|
|
|
|-----------|---------|
|
|
|
| **GPU** | NVIDIA H100 |
|
|
|
| **Framework** | Transformers + DeepSpeed |
|
|
|
| **Epochs** | 3 |
|
|
|
| **Learning Rate** | 2e-5 |
|
|
|
|
|
|
📊 **Training Report:** [WandB Dashboard](https://api.wandb.ai/links/batuhanozkose-org/pwcmt0or)
|
|
|
|
|
|
---
|
|
|
|
|
|
## 🧪 Training Dataset
|
|
|
|
|
|
The model was trained on [Rehber-CoT-Science](https://huggingface.co/datasets/batuhanozkose/Rehber-CoT-Science):
|
|
|
|
|
|
| Feature | Value |
|
|
|
|---------|-------|
|
|
|
| **Samples** | 712 verified QA pairs |
|
|
|
| **Domains** | Physics, Chemistry, Biology, Math, Statistics, Engineering, Science |
|
|
|
| **Difficulty** | 75% PhD, 25% Undergraduate |
|
|
|
| **Format** | Chain-of-Thought + Python Code |
|
|
|
| **Verification** | 100% (3-stage hybrid verification) |
|
|
|
|
|
|
---
|
|
|
|
|
|
## 💻 Usage
|
|
|
|
|
|
### Quick Start
|
|
|
|
|
|
```python
|
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
|
|
model_name = "batuhanozkose/Rehber-Science"
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
|
model_name,
|
|
|
torch_dtype="auto",
|
|
|
device_map="auto"
|
|
|
)
|
|
|
|
|
|
messages = [
|
|
|
{"role": "system", "content": """Sen akademik ve bilimsel sorularda uzman bir asistansın.
|
|
|
Her soruyu çözerken şu adımları takip et:
|
|
|
<think>
|
|
|
Düşünme süreci:
|
|
|
1. Soruyu analiz et - ne soruluyor?
|
|
|
2. İlgili kavramları ve formülleri belirle
|
|
|
3. Çözüm stratejisini planla
|
|
|
4. Olası hataları ve tuzakları düşün
|
|
|
5. Alternatif yaklaşımları değerlendir
|
|
|
</think>
|
|
|
Sonra adım adım çözümü yaz:
|
|
|
- Her adımı "Adım N:" formatında numaralandır
|
|
|
- Her adımda mantığını açıkla
|
|
|
- Formül kullanıyorsan göster
|
|
|
Son olarak:
|
|
|
- **Sonuç:** kısmında final cevabı ver
|
|
|
- **Doğrulama Kodu (Python):** kısmında kodu yaz
|
|
|
Türkçe cevap ver. Detaylı ve öğretici ol."""},
|
|
|
{"role": "user", "content": "Suyun elektrolizinde hangi gazlar açığa çıkar ve mol oranları nedir?"}
|
|
|
]
|
|
|
|
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
|
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
|
|
outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7)
|
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
|
```
|
|
|
|
|
|
### Loading Specific Version
|
|
|
|
|
|
```python
|
|
|
from transformers import AutoModelForCausalLM
|
|
|
|
|
|
# Latest version (v2)
|
|
|
model = AutoModelForCausalLM.from_pretrained("batuhanozkose/Rehber-Science")
|
|
|
|
|
|
# Previous version (v1)
|
|
|
model_v1 = AutoModelForCausalLM.from_pretrained("batuhanozkose/Rehber-Science", revision="v1")
|
|
|
```
|
|
|
|
|
|
### With vLLM (Recommended for Production)
|
|
|
|
|
|
```python
|
|
|
from vllm import LLM, SamplingParams
|
|
|
|
|
|
llm = LLM(model="batuhanozkose/Rehber-Science")
|
|
|
sampling_params = SamplingParams(temperature=0.7, max_tokens=1024)
|
|
|
|
|
|
prompts = ["Bir cismin serbest düşüş hızı nasıl hesaplanır?"]
|
|
|
outputs = llm.generate(prompts, sampling_params)
|
|
|
```
|
|
|
|
|
|
---
|
|
|
|
|
|
## 📝 Example Output
|
|
|
|
|
|
**Input:**
|
|
|
> Bir protonun 3.0 T manyetik alandaki Larmor frekansını hesaplayınız.
|
|
|
|
|
|
**Output:**
|
|
|
```
|
|
|
<think>
|
|
|
Düşünme süreci:
|
|
|
1. Larmor frekansı formülü: ω = γB
|
|
|
2. Protonun jiromanyetik oranı: γ = 2.675×10⁸ rad/s/T
|
|
|
3. Manyetik alan: B = 3.0 T
|
|
|
</think>
|
|
|
|
|
|
**Adım 1:** Larmor frekansı formülünü yazalım:
|
|
|
ω = γ × B
|
|
|
|
|
|
**Adım 2:** Değerleri yerleştirelim:
|
|
|
ω = 2.675×10⁸ rad/s/T × 3.0 T
|
|
|
|
|
|
**Adım 3:** Hesaplayalım:
|
|
|
ω = 8.025×10⁸ rad/s
|
|
|
|
|
|
**Sonuç:** 8.03×10⁸ rad/s
|
|
|
|
|
|
**Doğrulama Kodu (Python):**
|
|
|
```python
|
|
|
gamma = 2.675e8 # rad/s/T
|
|
|
B = 3.0 # Tesla
|
|
|
omega = gamma * B
|
|
|
print(f"{omega:.2e} rad/s") # Output: 8.03e+08 rad/s
|
|
|
```
|
|
|
```
|
|
|
|
|
|
---
|
|
|
|
|
|
## 🔬 Intended Use
|
|
|
|
|
|
### Primary Use Cases
|
|
|
- 📚 **Educational**: Helping students understand scientific concepts
|
|
|
- 🔬 **Research Assistance**: Quick calculations and formula verification
|
|
|
- 💻 **Code Generation**: Python code for scientific computations
|
|
|
- 📖 **Turkish STEM Content**: Academic Turkish scientific writing
|
|
|
|
|
|
### Limitations
|
|
|
- Not intended for critical scientific research without human verification
|
|
|
- May occasionally generate incorrect calculations
|
|
|
- Best performance on topics covered in training data
|
|
|
- Turkish language optimized, English support is secondary
|
|
|
|
|
|
---
|
|
|
|
|
|
## 📈 Evaluation
|
|
|
|
|
|
| Metric | Score |
|
|
|
|--------|-------|
|
|
|
| CoT Quality | 9.3/10 |
|
|
|
| Code Accuracy | 92% |
|
|
|
| Turkish Fluency | 9.0/10 |
|
|
|
| Scientific Depth | 9.5/10 |
|
|
|
|
|
|
---
|
|
|
|
|
|
## 📄 License
|
|
|
|
|
|
This model is released under the **Apache 2.0** license.
|
|
|
|
|
|
### Citation
|
|
|
|
|
|
```bibtex
|
|
|
@model{rehber_science_2025,
|
|
|
title={Rehber-Science: Turkish Scientific Reasoning Model},
|
|
|
author={Batuhan Ozkose},
|
|
|
year={2025},
|
|
|
publisher={Hugging Face},
|
|
|
url={https://huggingface.co/batuhanozkose/Rehber-Science},
|
|
|
base_model={Qwen/Qwen3-8B},
|
|
|
note={Fine-tuned for Chain-of-Thought scientific reasoning}
|
|
|
}
|
|
|
```
|
|
|
|
|
|
---
|
|
|
|
|
|
## 🙏 Acknowledgments
|
|
|
|
|
|
- [Qwen Team](https://github.com/QwenLM) for the excellent base model
|
|
|
- [Nebius AI](https://nebius.ai/) for training infrastructure
|
|
|
- [Hugging Face](https://huggingface.co/) for model hosting
|
|
|
- Turkish NLP community for feedback and support
|
|
|
|
|
|
---
|
|
|
|
|
|
<div align="center">
|
|
|
|
|
|
**Created by [Batuhan Ozkose](https://huggingface.co/batuhanozkose)**
|
|
|
|
|
|
Made with ❤️ for Turkish NLP Community
|
|
|
|
|
|
🎓 Scientific Reasoning • Chain-of-Thought • Verified Code 🎓
|
|
|
|
|
|
</div>
|
|
|
|
