feat: Change the used LLM

app.py

@@ -9,7 +9,7 @@ def llama3_1_8B(question):
     messages = [
     {"role": "user", "content": question},
     ]
-    pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-8B-Instruct")
+    pipe = pipeline("text-generation", model="NousResearch/Hermes-3-Llama-3.1-8B")
     responses = pipe(messages)
     return str(responses)