|
|
--- |
|
|
datasets: |
|
|
- ner_distillbert |
|
|
language: |
|
|
- en |
|
|
library_name: pytorch |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- ner |
|
|
- pytorch |
|
|
- mlflow |
|
|
task: token-classification |
|
|
--- |
|
|
|
|
|
# ner_distillbert |
|
|
|
|
|
## Model Description |
|
|
|
|
|
This is a Named Entity Recognition (NER) model based on DistilBERT, a distilled version of BERT that retains 97% of BERT's performance while being 60% smaller and faster. The model identifies and classifies named entities in text such as persons, organizations, locations, and other predefined categories. |
|
|
|
|
|
**Model Details:** |
|
|
- **Model Name:** ner_distillbert |
|
|
- **Version:** 1 |
|
|
- **Task:** Ner |
|
|
- **Framework:** pytorch |
|
|
- **Language(s):** en |
|
|
- **License:** apache-2.0 |
|
|
|
|
|
## Intended Uses |
|
|
|
|
|
This model is designed for ner tasks. Please evaluate on your specific use case before production deployment. |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Data |
|
|
- **Dataset:** ner_distillbert |
|
|
- **Dataset Size:** Not specified |
|
|
|
|
|
### Training Configuration |
|
|
|
|
|
## Usage |
|
|
|
|
|
### Installation |
|
|
```bash |
|
|
pip install transformers torch # For transformers models |
|
|
# OR |
|
|
pip install -r requirements.txt # For other frameworks |
|
|
``` |
|
|
|
|
|
### Basic Usage |
|
|
```python |
|
|
# Load and use the model |
|
|
from inference import Model # See inference.py in the repository |
|
|
|
|
|
model = Model(openchs/ner_distillbert_v1) |
|
|
predictions = model.predict([President Biden met with Chancellor Merkel at the White House to discuss NATO policies.]) |
|
|
print(predictions) |
|
|
``` |
|
|
|
|
|
## Performance Metrics |
|
|
|
|
|
### Evaluation Results |
|
|
| Metric | Value | |
|
|
|--------|-------| |
|
|
| Epoch | 3.0000 | |
|
|
| Eval Accuracy | 0.9608 | |
|
|
| Eval F1 | 0.9433 | |
|
|
| Eval Loss | 0.1171 | |
|
|
| Eval Precision | 0.9324 | |
|
|
| Eval Recall | 0.9608 | |
|
|
| Eval Runtime | 0.1943 | |
|
|
| Eval Samples Per Second | 82.3410 | |
|
|
| Eval Steps Per Second | 10.2930 | |
|
|
|
|
|
## MLflow Tracking |
|
|
|
|
|
- **Experiment:** N/A |
|
|
- **Run ID:** `N/A` |
|
|
- **Training Date:** N/A |
|
|
|
|
|
## Citation |
|
|
|
|
|
```bibtex |
|
|
@misc{ner_distillbert_1, |
|
|
title={ner_distillbert}, |
|
|
author={BITZ-AI TEAM}, |
|
|
year={2025}, |
|
|
publisher={Hugging Face}, |
|
|
url={https://huggingface.co/marlonbino/ner_distillbert} |
|
|
} |
|
|
``` |
|
|
|
