Update app.py

app.py

@@ -39,7 +39,9 @@ openllama_pipeline = pipeline(
     "text-generation",
     model=model,
     tokenizer=tokenizer,
-    device=0 if torch.cuda.is_available() else -1  # Use GPU if available
+    truncation=True,  # Add this line
+    max_length=max_tokens,  # Assuming max_tokens is your max_length variable
+    # ... other parameters
 )
 
 nlp = AutoTokenizer.from_pretrained("bert-base-uncased")