Add detailed model card with comprehensive documentation

README.md

@@ -1,199 +1,168 @@
 ---
-library_name: transformers
-tags: []
+language: tr
+tags:
+- turkish
+- conspiracy-detection
+- bert
+- classification
+- text-classification
+- fine-tuned
+license: apache-2.0
+datasets:
+- custom
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: turkish-conspiracy-detection
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      type: custom
+      name: Turkish Conspiracy Detection Dataset
+    metrics:
+    - type: accuracy
+      value: 0.9879
+      name: Accuracy
+    - type: f1
+      value: 0.9879
+      name: F1 Score
+    - type: precision
+      value: 0.9879
+      name: Precision
+    - type: recall
+      value: 0.9879
+      name: Recall
 ---
 
-# Model Card for Model ID
+# Türkçe Komplo Teorisi Tespit Modeli
 
-<!-- Provide a quick summary of what the model is/does. -->
+Bu model, Türkçe metinlerde komplo teorisi tespiti yapmak için fine-tune edilmiş BERT tabanlı bir sınıflandırma modelidir.
 
+## Model Detayları
 
+### Model Açıklaması
+- **Geliştirici**: Metinimo19
+- **Model Türü**: Text Classification (İkili Sınıflandırma)
+- **Dil**: Türkçe (tr)
+- **Temel Model**: [savasy/bert-base-turkish-sentiment-cased](https://huggingface.co/savasy/bert-base-turkish-sentiment-cased)
+- **Fine-tuning Görevi**: Komplo teorisi vs gerçek haber ayrımı
+- **Lisans**: Apache 2.0
 
-## Model Details
+### Model Kaynakları
+- **Repository**: https://huggingface.co/Metinimo19/turkish-conspiracy-detection
+- **Temel Model**: https://huggingface.co/savasy/bert-base-turkish-sentiment-cased
 
-### Model Description
+## Kullanım
 
-<!-- Provide a longer summary of what this model is. -->
+### Doğrudan Kullanım
+Model, Türkçe metinlerde komplo teorisi tespiti için kullanılabilir:
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+# Model ve tokenizer'ı yükle
+tokenizer = AutoTokenizer.from_pretrained("Metinimo19/turkish-conspiracy-detection")
+model = AutoModelForSequenceClassification.from_pretrained("Metinimo19/turkish-conspiracy-detection")
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+# Örnek metin
+text = "5G teknolojisi insanları kontrol etmek için tasarlanmış gizli bir sistemdir."
 
-### Model Sources [optional]
+# Tahmin yap
+inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    predicted_class = torch.argmax(predictions, dim=-1).item()
 
-<!-- Provide the basic links for the model. -->
+# Sonuç
+result = "Komplo Teorisi" if predicted_class == 1 else "Gerçek Haber"
+confidence = predictions[0][predicted_class].item()
+print(f"Tahmin: {result} (Güven: {confidence:.2%})")
+```
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+## Eğitim Detayları
 
-## Uses
+### Eğitim Verisi
+- **Veri Seti Boyutu**: 1,651 Türkçe örnek
+- **Sınıf Dağılımı**: Dengeli (yaklaşık %50 gerçek haber, %50 komplo teorisi)
+- **Veri Türü**: Türkçe metinler (haberler, sosyal medya içerikleri, makale özetleri)
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### Eğitim Prosedürü
 
-### Direct Use
+#### Eğitim Hiperparametreleri
+- **Batch Size**: 16 (train ve eval)
+- **Learning Rate**: 2e-5
+- **Epochs**: 3
+- **Warmup Steps**: 500
+- **Weight Decay**: 0.01
+- **Optimizer**: AdamW
+- **Mixed Precision**: FP16 (GPU kullanımında)
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+#### Veri Bölünmesi
+- **Eğitim**: %70 (1,155 örnek)
+- **Doğrulama**: %15 (248 örnek)
+- **Test**: %15 (248 örnek)
 
-[More Information Needed]
+## Değerlendirme
 
-### Downstream Use [optional]
+### Test Sonuçları
+Model test seti üzerinde şu performansı gösterdi:
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+| Metrik | Değer |
+|--------|-------|
+| **Accuracy** | 0.9879 |
+| **F1 Score** | 0.9879 |
+| **Precision** | 0.9879 |
+| **Recall** | 0.9879 |
 
-[More Information Needed]
+### Sınıf Tanımları
+- **0**: Gerçek Haber - Doğrulanabilir, güvenilir kaynaklardan gelen bilgiler
+- **1**: Komplo Teorisi - Kanıtlanmamış, spekülatif veya yanlış bilgiler
 
-### Out-of-Scope Use
+## Sınırlamalar ve Önyargılar
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+### Sınırlamalar
+- Model sadece Türkçe metinler için eğitilmiştir
+- 512 token uzunluğundaki metinlerle sınırlıdır
+- Eğitim verisinin boyutu nispeten küçüktür (1,651 örnek)
+- Belirli konularda (5G, aşı, uzaylılar vb.) daha fazla veri içerir
 
-[More Information Needed]
+### Öneriler
+- Kritik kararlar için model çıktılarını tek başına kullanmayın
+- Sonuçları uzman değerlendirmesiyle destekleyin
+- Modelin sınırlarını göz önünde bulundurun
 
-## Bias, Risks, and Limitations
+## Teknik Özellikler
+
+### Model Mimarisi
+- **Temel Mimari**: BERT (Bidirectional Encoder Representations from Transformers)
+- **Parametre Sayısı**: ~110M parametre
+- **Sınıflandırma Katmanı**: Linear layer (768 → 2)
+- **Aktivasyon**: Softmax
+
+### Hesaplama Altyapısı
+- **Eğitim Platformu**: Google Colab
+- **GPU**: Tesla T4 (16GB)
+- **Eğitim Süresi**: Yaklaşık 10-15 dakika
+- **Framework**: PyTorch + Transformers
+
+## Nasıl Başlanır
+
+```python
+from transformers import pipeline
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+# Pipeline kullanarak basit kullanım
+classifier = pipeline("text-classification", model="Metinimo19/turkish-conspiracy-detection")
+result = classifier("Ay'a hiç çıkmadık, tüm görüntüler sahteydi.")
+print(result)
+```
 
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
+---
 
-[More Information Needed]
+*Bu model, eğitim ve araştırma amaçları için geliştirilmiştir. Üretim ortamında kullanmadan önce kapsamlı testler yapılması önerilir.*