using gpt2- as it was not gated

app.py

@@ -87,7 +87,7 @@ def using_ollama_model(retriever, query, results, conversation_history):
     )
     
     doc_texts = "\\n".join([doc.page_content for doc in results])
-    model_id = "meta-llama/Llama-3.2-1B-Instruct"
+    model_id = "gpt2"
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     model = AutoModelForCausalLM.from_pretrained(model_id)
     pipe = pipeline(