Downloads · 30 days
6
4% of all-time downloads
Mozkyy/ner-laporgub-jateng
ner-laporgub-jateng is a token classification model from Mozkyy. Use it when you need labels on individual words, such as names. The card lists the license as mit.
Model Named Entity Recognition (NER) untuk mengekstrak entitas lokasi dari laporan ke Gubernur Jawa Tengah.
Downloads · 30 days
6
4% of all-time downloads
All-time downloads
142
Public
Repo size
880 MB
Likes
0
Public
Click a slice to open those files.
.h5440 MB · 100%
From the Hugging Face model README
Model Named Entity Recognition (NER) untuk mengekstrak entitas lokasi dari laporan ke Gubernur Jawa Tengah.
Model ini dilatih untuk mendeteksi entitas lokasi seperti:
Model ini cocok untuk:
from transformers import AutoTokenizer, TFAutoModelForTokenClassification, pipeline
# Load model
model_name = "Mozkyy/ner-laporgub-jateng"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = TFAutoModelForTokenClassification.from_pretrained(model_name)
# Create pipeline
nlp = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
# Test
text = "Jalan rusak di Desa Karanganyar Kabupaten Demak sangat parah"
results = nlp(text)
for entity in results:
print(f"{entity['word']} -> {entity['entity_group']} (score: {entity['score']:.2f})")
Dataset: Laporan masyarakat ke Gubernur Jawa Tengah
Jika menggunakan model ini dalam penelitian, mohon sitasi:
@misc{ner-laporgub-jateng,
author = {Mozkyy},
title = {NER Model untuk Laporan Gubernur Jawa Tengah},
year = {2025},
publisher = {Hugging Face},
howpublished = {\url{https://huggingface.co/USERNAME/ner-laporgub-jateng}}
}
3. **Ganti `USERNAME`** dengan username Hugging Face Anda
4. **Klik "Commit new file to main"**
## Langkah 6: Verifikasi Upload Berhasil
1. **Cek tab "Files and versions"** - pastikan semua file ada:
✅ README.md ✅ config.json ✅ tf_model.h5 ✅ tokenizer_config.json ✅ vocab.txt (atau tokenizer.json) ✅ special_tokens_map.json