# RoBERTa Multitask Model

This is a multitask model based on RoBERTa, trained for:

- Sentiment Analysis (negative, neutral, positive)
- Emotion Classification (anger, joy, optimism, sadness)
- Hate Speech Detection (hate, offensive, neither)

It uses a shared encoder with task-specific heads.

## Usage

```python
from models.multitask_model import MultiTaskModel
from transformers import RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained("roberta-base")
model = MultiTaskModel.from_pretrained("SeragAmin/RoBERTa_Multitask")