Update app.py

app.py

@@ -34,7 +34,6 @@ model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
 
 def respond(
     message: str,
-    history: list[tuple[str, str]],
     system_message: str,
     max_tokens: int = 128,
     temperature: float = 1.0,
@@ -62,49 +61,15 @@ def respond(
     generation_thread.start()
 
     # Stream the output progressively
+    generated_text = ""
     for token in streamer:  # Append each token to the accumulated text
-        yield token
+        generated_text += token
+        yield generated_text
 
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-# demo = gr.ChatInterface(
-#     respond,
-#     additional_inputs=[
-#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-#         gr.Slider(
-#             minimum=0.1,
-#             maximum=1.0,
-#             value=0.95,
-#             step=0.05,
-#             label="Top-p (nucleus sampling)",
-#         ),
-#     ],
-# )
-
-# Function to process translation
-def respond_google_translate(
-    source_text,
-    system_message,
-    max_tokens,
-    temperature,
-    top_p
-):
-    # Call the respond function and collect the final response
-    result = ""
-    for token in respond(
-        message=source_text,
-        history=[],
-        system_message=system_message,
-        max_tokens=max_tokens,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        result += token  # Accumulate the tokens
-    return result
 
 # Define the interface
 with gr.Blocks() as demo:
@@ -144,7 +109,7 @@ with gr.Blocks() as demo:
 
     # Define functionality
     translate_button.click(
-        respond_google_translate,
+        respond,
         inputs=[
             source_textbox,
             system_message_input,