You can deploy this model and start earning money today!

Avvirup/
custom-bert-finetuned

Views

No views yet

Model Card for Model ID

Model Details

This is a fine-tuned BERT-based model for classifying text into three emotions: sadness, joy, and anger. It was built using Hugging Face Transformers and PyTorch.

Model Description

Developed by: Avirup Dasgupta
Model type: Transformers – Sequence Classification
Language(s) (NLP): English
License: MIT
Finetuned from model: bert-base-uncased

Uses

Direct Use

Emotion detection from text inputs
Sentiment analysis pipelines
Chatbots or customer support systems to detect user mood

Downstream Use [optional]

Emotion-aware recommendation systems
Mental health monitoring tools (with caution)

Out-of-Scope Use

Legal, medical, or financial advice
Detecting sarcasm, complex emotions, or nuanced human affect

Bias, Risks, and Limitations

Model may misclassify nuanced emotions.
Limited to English text.
Trained on a specific dataset – may reflect its biases.
Not suitable for high-stakes or medical decisions.

[More Information Needed]

Recommendations

Users should validate predictions for critical use cases and combine model outputs with human oversight.

How to Get Started with the Model

python

from transformers import BertTokenizer, BertForSequenceClassification
import torch

# Load the tokenizer and model from Hugging Face
tokenizer = BertTokenizer.from_pretrained("Avvirup/emotion-bert-multiclass")
model = BertForSequenceClassification.from_pretrained("Avvirup/emotion-bert-multiclass")

# Example text
text = "I am feeling really happy today!"

# Tokenize the text
inputs = tokenizer(
    text, 
    return_tensors="pt", 
    truncation=True, 
    padding="max_length", 
    max_length=128
)

# Make prediction
with torch.no_grad():
    outputs = model(**inputs)
    prediction = torch.argmax(outputs.logits, dim=1).item()
    
# Map prediction to emotion label
label_names = ["sadness", "joy", "anger"]
print(f"Prediction: {label_names[prediction]}")

Avvirup/custom-bert-finetuned