init inference

app.py

@@ -15,36 +15,33 @@ 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})
-
+    # Combine the system message and chat history into a single string
+    prompt = system_message + "\n"
+    for user_input, assistant_reply in history:
+        if user_input:
+            prompt += f"User: {user_input}\n"
+        if assistant_reply:
+            prompt += f"Assistant: {assistant_reply}\n"
+    prompt += f"User: {message}\nAssistant:"
+
+    # Send the request to the model
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    for token in client.text_generation(
+        prompt,
+        max_new_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
+        response += token.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,
+    type="messages",
     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"),