Update helper.py

helper.py

@@ -21,7 +21,6 @@ def get_fn(model_name: str, **model_kwargs) -> Callable:
         messages: list,  # Preprocessed messages from preprocess function
         temperature: float,
         max_tokens: int,
-        repetition_penalty: float,
         top_p: float
     ) -> Generator[str, None, None]:
         try:
@@ -31,7 +30,6 @@ def get_fn(model_name: str, **model_kwargs) -> Callable:
                 messages=messages,
                 temperature=temperature,
                 max_tokens=max_tokens,
-                repetition_penalty=repetition_penalty,
                 top_p=top_p,
                 stream=True, 
                 # Ensure response_format is set correctly; typically it's a string like 'text'
@@ -129,7 +127,6 @@ def registry(name: str = None, **kwargs) -> gr.ChatInterface:
             messages=messages,
             temperature=temperature,
             max_tokens=max_tokens,
-            repetition_penalty=repetition_penalty,
             top_p=top_p
         )
         
@@ -150,7 +147,6 @@ def registry(name: str = None, **kwargs) -> gr.ChatInterface:
             ),
             gr.Slider(0.0, 1.0, value=0.7, label="Temperature"),
             gr.Slider(128, 4096, value=1024, label="Max new tokens"),
-            gr.Slider(0.0, 2.0, value=1.1, label="Repetition penalty"),
             gr.Slider(0.0, 1.0, value=0.95, label="Top P sampling"),
         ],
     )