fix slicing

app.py

@@ -16,7 +16,7 @@ def generate_response(prompt):
     inputs = tokenizer(prompt, return_tensors="pt")
     outputs = model.generate(**inputs, max_new_tokens=5, temperature=1.0)
     full_output = tokenizer.decode(outputs[0], skip_special_tokens=False)
-    new_tokens = full_output[len(prompt):]
+    new_tokens = full_output[len(inputs):]
     return new_tokens
 
 iface = gr.Interface(