Text Classification
Transformers
Safetensors
Indonesian
bert
clickbait
indonesian
text-embeddings-inference
Instructions to use midlyn/indobert-clickbait-id with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use midlyn/indobert-clickbait-id with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="midlyn/indobert-clickbait-id")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("midlyn/indobert-clickbait-id") model = AutoModelForSequenceClassification.from_pretrained("midlyn/indobert-clickbait-id", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Deteksi clickbait judul berita berbahasa Indonesia
Hasil fine-tuning indobenchmark/indobert-base-p1 pada dataset CLICK-ID (klasifikasi biner: clickbait / non-clickbait).
- Max length: 64 token
- Test set (1.496 judul): accuracy 0.7266, F1 (macro) 0.6982
Model dibuat untuk keperluan penelitian skripsi. Label dataset berasal dari annotator manusia yang tidak selalu sepakat, sehingga prediksi bukan kebenaran mutlak.
- Downloads last month
- 13
Model tree for midlyn/indobert-clickbait-id
Base model
indobenchmark/indobert-base-p1