---
datasets:
- Mr-Vicky-01/Security-QnA
license: apache-2.0
---

## INFERENCE CODE
```bash
pip install transformers[torch]
```

```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch
import time

tokenizer = AutoTokenizer.from_pretrained("Mr-Vicky-01/QnA-248M")
model = AutoModelForSeq2SeqLM.from_pretrained("Mr-Vicky-01/QnA-248M")

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

prefix = "Answer the Question: "
inp = YOUR_QUESTION

import time
start = time.time()

inputs = tokenizer(prefix + inp.lower(), return_tensors="pt")
model.to(device)
inputs = inputs.to(device)
outputs = model.generate(**inputs, max_length=512)
answer = tokenizer.decode(outputs[0], skip_special_tokens=True).strip()
print(answer)

end = time.time()
print(f"Time taken: {end - start}")
```