# Urdu GPT Model

This is a GPT model trained on Urdu text data.

## Model Details
- Architecture: GPT-2 style
- Vocabulary Size: 50257
- Context Length: 256
- Embedding Dimension: 768
- Number of Layers: 12
- Number of Heads: 12

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("your-username/model-name")
tokenizer = AutoTokenizer.from_pretrained("your-username/model-name")

# Generate text
text = "عشق"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs)
result = tokenizer.decode(outputs[0])
```