Update app.py

app.py

@@ -35,7 +35,7 @@ client = InferenceClient(
 
 VERBOSE = True
 MAX_HISTORY = 100
-MODEL = "gpt-3.5-turbo"  # "gpt-4"
+MODEL = mistralai/Mixtral-8x7B-Instruct-v0.1"
 
 
 def format_prompt(message, history):
@@ -93,7 +93,7 @@ def compress_history(purpose, task, history, directory):
     resp = run_gpt(
         COMPRESS_HISTORY_PROMPT,
         stop_tokens=["observation:", "task:", "action:", "thought:"],
-        max_tokens=512,
+        max_tokens=5096,
         purpose=purpose,
         task=task,
         history=history,