Update app.py

app.py

@@ -25,7 +25,7 @@ models = {name: AutoModelForCausalLM.from_pretrained(model_id, device_map="auto"
 tokenizers = {name: AutoTokenizer.from_pretrained(model_id) for name, model_id in model_details.items()}
 
 @spaces.GPU(enable_queue=True, duration=90)
-async def generate(
+def generate(
     model_choice: str,
     message: str,
     chat_history: list[tuple[str, str]],
@@ -38,7 +38,7 @@ async def generate(
 ) -> str:
     model = models[model_choice]
     tokenizer = tokenizers[model_choice]
-    
+
     conversation = [{"role": "system", "content": system_prompt}] if system_prompt else []
     conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}] for user, assistant in chat_history)
     conversation.append({"role": "user", "content": message})
@@ -51,6 +51,7 @@ async def generate(
 
     return output_text
 
+
 chat_interface = gr.ChatInterface(
     theme='ehristoforu/RE_Theme',
     fn=generate,