| --- |
| library_name: transformers |
| tags: [] |
| --- |
| |
| # Model Card for Model ID |
|
|
| <!-- Provide a quick summary of what the model is/does. --> |
|
|
| # BERT NER Model (CoNLL-2003) |
|
|
| ## 📌 Overview |
| This model is a fine-tuned version of `bert-base-cased` for the task of Named Entity Recognition (NER). |
|
|
| ## 🎯 Task |
| Token Classification (Named Entity Recognition) |
|
|
| The model identifies the following entity types: |
| - PER (Person) |
| - ORG (Organization) |
| - LOC (Location) |
| - MISC (Miscellaneous) |
|
|
| ## 📊 Dataset |
| - CoNLL-2003 (English news dataset) |
| - Only NER tags were used (BIO format) |
|
|
| ## 🧠 Model Details |
| - Base model: `bert-base-cased` |
| - Architecture: Transformer Encoder (BERT) |
| - Fine-tuning: Hugging Face Transformers |
| - Training epochs: 3 |
|
|
| ## 📈 Performance |
| Test set results: |
| - Precision: ~0.90 |
| - Recall: ~0.91 |
| - F1-score: ~0.91 |
| - Accuracy: ~0.98 |
|
|
| ## ⚙️ Usage Example |
|
|
| ```python |
| from transformers import pipeline |
| |
| ner = pipeline( |
| "ner", |
| model="x4n4/bert-conll2003-ner", |
| aggregation_strategy="simple" |
| ) |
| |
| text = "Barack Obama visited Google in New York" |
| print(ner(text)) |
