move the model to the endpoint as well

app/bot.py

@@ -183,8 +183,7 @@ async def on_message(ctx):
                     "role": "user",
                 },
             ],
-            "model": "llama2-chat-7b",
+            "model": requests.get(llm_rule_endpoint).json()["model"],
-            # "model": "mistral-ins-7b-q4",
             "stream": False,
             "max_tokens": 4096,
             "stop": ["goon"],