Update app.py

app.py

@@ -18,8 +18,6 @@ def reply(message, history):
     inputs = tokenizer(prompt.format(m), return_tensors="pt")
     outputs = model.generate(**inputs)
     code=tokenizer.batch_decode(outputs, skip_special_tokens=True)
-    for i in range(len(code)):
-        time.sleep(0.3)
-        yield  code[: i+1]
+    return code
 
-gr.ChatInterface(reply).queue().launch()
+gr.ChatInterface(reply).launch()