Update app.py

app.py

@@ -55,15 +55,12 @@ class OrcaChatBot:
             top_p=top_p,
             repetition_penalty=repetition_penalty,
             pad_token_id=self.tokenizer.eos_token_id,
-            do_sample=True, 
-            skip_prompt=True,
-            skip_special_tokens=True
-        )
-
-        response = self.tokenizer.decode(output_ids[0], skip_special_tokens=True)
-        self.update_conversation_history("", response)
-        return response
+            do_sample=True
+    )
 
+    response = self.tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    self.update_conversation_history("", response)
+    return response
 Orca_bot = OrcaChatBot(model, tokenizer)
 
 def gradio_predict(user_message, system_message, max_new_tokens, temperature, top_p, repetition_penalty):