Atherizz/emolog-indobert

Emolog IndoBERT (Fine-tuned for Emotion Classification in Indonesian)

🚀 This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an Indonesian emotion classification dataset.
It is trained to classify user-written daily mood/feeling texts into several emotional categories.

---

🧠 Model Details

• Model Name: Emolog IndoBERT
• Base Model: indobenchmark/indobert-base-p2
• Fine-tuned by: Atherizz
• Language: Indonesian (id)
• Task: Text Classification (Emotion Detection)
• License: Apache 2.0
• Dataset: Chipan/indonesia-5-emotion-cls-dataset
• Trained using: Hugging Face Transformers & PyTorch

---

📊 Labels (Emotions)

The model is trained to predict the following emotions:

• Senang (Happy)
• Sedih (Sad)
• Marah (Angry)
• Takut (Fear)
• Jijik (Disgust)
• Terkejut (Surprise)
• Netral

---

📦 Usage

You can use this model directly with the transformers library:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("Atherizz/emolog-indobert")
model = AutoModelForSequenceClassification.from_pretrained("Atherizz/emolog-indobert")

inputs = tokenizer("aku capek dan bingung hari ini", return_tensors="pt")
outputs = model(**inputs)
predicted_class = torch.argmax(outputs.logits)
print(predicted_class)