Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 import os
 import spaces
-from transformers import GemmaTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 from threading import Thread
 
@@ -77,7 +77,7 @@ def chat_openchat_36(message: str,
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": message})
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(model.device)
     
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)