Update app.py

app.py

@@ -1,7 +1,7 @@
 import os
 import gradio as gr
 import spaces
-from transformers import AutoTokenizer, AutoModel
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
 
 model_name = "teknium/OpenHermes-2.5-Mistral-7B"
@@ -20,9 +20,8 @@ Suggest only up to 5 works ahead.
 
 @spaces.GPU
 def generate(text):
-    data = [
+    messages = [
         {'role': 'system', 'content': system_prompt},
         {'role': 'user', 'content': text}
     ]
-    tokenized = tokenizer.apply_chat_template(data, return_tensors='pt')
-    return tokenizer.deocode(model.generate(**tokenized).squeeze(0))
+    return pipe(messages)