Update app.py

app.py

@@ -10,6 +10,7 @@ def greet_json():
 
 @app.get("/hello/{msg}")
 def say_hello(msg: str):
+    print("model")
     torch.random.manual_seed(0) 
     model = AutoModelForCausalLM.from_pretrained( 
         "microsoft/Phi-3-mini-128k-instruct",  
@@ -17,7 +18,7 @@ def say_hello(msg: str):
         torch_dtype="auto",  
         trust_remote_code=True,  
     ) 
-
+    print("token & msg")
     tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct") 
 
     messages = [ 
@@ -26,13 +27,13 @@ def say_hello(msg: str):
         {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, 
         {"role": "user", "content": msg}, 
     ] 
-
+    print("pipe")
     pipe = pipeline( 
         "text-generation", 
         model=model, 
         tokenizer=tokenizer, 
     ) 
-
+    print("output")
     generation_args = { 
         "max_new_tokens": 500, 
         "return_full_text": False, 
@@ -41,4 +42,5 @@ def say_hello(msg: str):
     } 
 
     output = pipe(messages, **generation_args) 
+    print("complete")
     return {"message": output[0]['generated_text']}