Update app.py

app.py

@@ -16,7 +16,7 @@ def chat_with_bot(prompt):
     length = 18 + len(prompt)
     # Generate a response
     with torch.no_grad():
-        outputs = inference.generate(inputs['input_ids'], attention_mask=inputs['attention_mask'],max_new_tokens=50, num_return_sequences=1, pad_token_id=tokenizer.pad_token_id)
+        outputs = model.generate(inputs['input_ids'], attention_mask=inputs['attention_mask'],max_new_tokens=50, num_return_sequences=1, pad_token_id=tokenizer.pad_token_id)
 
     # Decode and return the response
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)