Update app.py

app.py

@@ -20,7 +20,7 @@ def generate_response(passage: str, question: str) -> str:
 
     prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
     inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
-    response = model.generate(input_ids=inputs.to(olmo.device), max_new_tokens=100)
+    response = model.generate(input_ids=inputs.to(model.device), max_new_tokens=100)
     
     response = tokenizer.batch_decode(response, skip_special_tokens=True)[0]