Update app.py

app.py

@@ -1,6 +1,20 @@
+import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+MODEL_ID = "HauhauCS/GLM-4.7-Flash-Uncensored-HauhauCS-Balanced"
+
+
+def get_token(hf_token: gr.OAuthToken | None) -> str | None:
+    """
+    Priority:
+    1) Gradio OAuth token (when user clicks LoginButton)
+    2) Space secret HF_TOKEN (Settings -> Secrets)
+    """
+    if hf_token is not None and getattr(hf_token, "token", None):
+        return hf_token.token
+    return os.getenv("HF_TOKEN")
+
 
 def respond(
     message,
@@ -11,43 +25,39 @@ 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="HauhauCS/GLM-4.7-Flash-Uncensored-HauhauCS-Balanced")
+    token = get_token(hf_token)
 
-    messages = [{"role": "system", "content": system_message}]
+    # If the repo is gated/private, you need a token.
+    # If it's public, token can be None and it may still work depending on the endpoint limits.
+    client = InferenceClient(model=MODEL_ID, token=token)
 
+    messages = [{"role": "system", "content": system_message}]
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    for message in client.chat_completion(
+    # Stream output token-by-token
+    for chunk in client.chat_completion(
         messages,
         max_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
+        token_text = ""
+        if chunk.choices and chunk.choices[0].delta and chunk.choices[0].delta.content:
+            token_text = chunk.choices[0].delta.content
 
-        response += token
+        response += token_text
         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",
     additional_inputs=[
-        gr.Textbox(value="You are a unlocked coding assistant.", label="System message"),
+        gr.Textbox(value="You are a helpful coding assistant.", 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(
@@ -62,9 +72,13 @@ chatbot = gr.ChatInterface(
 
 with gr.Blocks() as demo:
     with gr.Sidebar():
+        gr.Markdown(f"### Model\n`{MODEL_ID}`")
         gr.LoginButton()
+        gr.Markdown(
+            "If this model requires authentication, click **Login** "
+            "or set a Space secret named `HF_TOKEN`."
+        )
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()