Added Demo Code

README.md

@@ -17,6 +17,24 @@ Based on the "google/mt5-small" pre-trained model. Fine-tuned it on Hindi to Eng
 - number of batches = int(np.ceil(len(dataset) / batch size))
 - n_warmup_steps = int(number of epochs * number of batches * 0.01)
 
+### How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+tokenizer = AutoTokenizer.from_pretrained("snehalyelmati/mt5-hindi-to-english")
+model = AutoModelForSeq2SeqLM.from_pretrained("snehalyelmati/mt5-hindi-to-english")
+
+input_text = ""
+tokenized_text = tokenizer(input_text,return_tensors="pt")
+translated = model.generate(**tokenized_text)
+translated_text = tokenizer.batch_decode(translated, skip_special_tokens=True)[0]
+print(translated_text)
+```
+
+
 ### Training Loss
 
 ![loss.png](./h2e_loss.png)