Update app.py

app.py

@@ -24,8 +24,8 @@ def check_and_download_model():
     
     # Use TinyLlama - a fully public model
     # model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
-    # model_name = "unsloth/functiongemma-270m-it"
-    model_name = "Qwen/Qwen3-0.6B"
+    model_name = "unsloth/functiongemma-270m-it"
+    # model_name = "Qwen/Qwen3-0.6B"
     cache_dir = "./my_model_cache"
     
     # Check if model already exists in cache
@@ -142,7 +142,7 @@ def openai_chat_completions(request: dict):
     
     messages = request.get("messages", [])
     model = request.get("model", model_name)
-    max_tokens = request.get("max_tokens", 100)
+    max_tokens = request.get("max_tokens", 1000)
     temperature = request.get("temperature", 0.7)
     
     print('\n\n request')
@@ -162,17 +162,8 @@ def openai_chat_completions(request: dict):
         max_new_tokens=max_tokens,
         # temperature=temperature
     )
-    print('\n\n asdfasdfasdfasdf')
-    print('result')
-    print(result)
-    print('data over \n\n')
-
 
     result = convert_json_format(result)
-    print('\n\n 33333333333333333333333')
-    print('result')
-    print(result)
-    print('data over 3333 \n\n')
 
     
     completion_id = f"chatcmpl-{int(time.time())}"