Update app.py

app.py

@@ -224,8 +224,11 @@ def get_llama_response(message: str, history: list) -> str:
 
   #print(template)
   chain.prompt=prompt
-  res = chain(query_text)
-  return(res["response"])
+  #res = chain(query_text)
+  inputs = tokenizer(query_text, return_tensors="pt")
+  outputs = model.generate(inputs.input_ids, max_length=50)
+  response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+  return(response)
 
 import gradio as gr