change the template from chat to text generation

app.py

@@ -1,12 +1,13 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import spaces
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 client = InferenceClient("veechan/gpt-neo-1.3B-platypus-finetuned")
 
-
+@spaces.GPU
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,33 +16,25 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
+    # Construct the prompt
+    prompt = system_message + "\n\n"
+    for user_msg, bot_msg in history:
+        prompt += f"Human: {user_msg}\nAI: {bot_msg}\n"
+    prompt += f"Human: {message}\nAI:"
 
     response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    for token in client.text_generation(
+        prompt,
+        model=model,
+        max_new_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +51,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()