soheil-mp/EmoBERT

Custom BERT Multi-Label Emotion Classifier

This model is a fine-tuned BERT model for multi-label emotion classification. It predicts:

• Main emotions: happiness, sadness, anger, fear, disgust, surprise, neutral
• Sub-emotions: more granular emotional states (curiosity, pride, etc.)
• Intensity: mild, moderate, neutral

Model Details

• Base model: BERT-base-uncased
• Fine-tuned for multi-label emotion classification
• Training dataset size: {train_size} samples
• Validation accuracy: {val_acc}

Usage

from transformers import AutoTokenizer, AutoModel
import torch

# Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("soheil-mp/EmoBERT")
model = BertModel.from_pretrained("soheil-mp/EmoBERT")

# Prepare input
text = "I'm so excited about the upcoming concert!"
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)

# Get predictions
outputs = model(**inputs)

Limitations

• TBA

Training Details

• TBA