Update app.py

app.py

@@ -29,12 +29,17 @@ llm = ctransformers.AutoModelForCausalLM.from_pretrained('./llama-2-7b.ggmlv3.q4
 print("Loaded model")
 
 def complete(prompt, stop=["User", "Assistant"]):
+    print("0")
     tokens = llm.tokenize(prompt)
+    print("1")
     token_count = 0
     output = ''
+    print("2")
     for token in llm.generate(tokens):
+        print("tokens")
         token_count += 1
         result = llm.detokenize(token)
+        print("detokens")
         output += result
         for word in stop:
             if word in output: