update app.py

app.py

@@ -2,6 +2,27 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 
 
+def format_chat_messages(messages):
+    """
+    Converts Gradio message history into a single text prompt
+    in ChatML / Llama-3-like format.
+    """
+    prompt = ""
+    for msg in messages:
+        role = msg["role"]
+        content = msg["content"]
+
+        if role == "system":
+            prompt += f"<|system|>\n{content}\n"
+        elif role == "user":
+            prompt += f"<|user|>\n{content}\n"
+        else:
+            prompt += f"<|assistant|>\n{content}\n"
+
+    prompt += "<|assistant|>\n"  # assistant is about to reply
+    return prompt
+
+
 def respond(
     message,
     history: list[dict[str, str]],
@@ -11,38 +32,39 @@ def respond(
     top_p,
     hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="Selinaliu1030/lora_model")
+    # explicitly specify provider (IMPORTANT for avoiding StopIteration)
+    client = InferenceClient(
+        model="Selinaliu1030/lora_model",
+        token=hf_token.token,
+        provider="hf-inference"   # <-- ⭐ REQUIRED FIX
+    )
 
+    # Build the message list
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
+    # Convert messages into single prompt
+    prompt = format_chat_messages(messages)
+
     response = ""
 
-    for message in client.text_generation(
-        messages,
+    # Use the correct API for text generation (not chat endpoints)
+    for msg in client.text_generation(
+        prompt,
         max_new_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
         token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        if msg.token:   # new API returns .token
+            token = msg.token
 
         response += token
         yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
@@ -65,8 +87,5 @@ with gr.Blocks() as demo:
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()
-
-