Update app.py

app.py

@@ -12,8 +12,8 @@ llama = llama_cpp.Llama.from_pretrained(
     tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B"),
     verbose=False,
      n_ctx=4096,
-        n_threads=4,
         n_gpu_layers=0,
+    chat_format="llama-2"
 )
 # Logger setup
 logging.basicConfig(level=logging.INFO)
@@ -74,7 +74,11 @@ async def complete(
             ],
             temperature=temperature,
             seed=seed,
+            echo=True, 
+            stream=True
         )
+        for item in output:
+            print(item['choices'][0]['text'], end='')
         et = time()
         output["time"] = et - st
         return output