Update app.py

app.py

@@ -1,70 +1,100 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+import litellm
 
+DESCRIPTION = '''
+<div>
+<h1 style="text-align: center;">TAIDE/Gemma-3-TAIDE-12b-Chat</h1>
+<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/taide/Gemma-3-TAIDE-12b-Chat"><b>Gemma-3-TAIDE-12b-Chat</b></a>. Gemma-3-TAIDE-12b-Chat is the new open LLM and comes in one sizes: 8b. Feel free to play with it, or duplicate to run privately!</p>
+</div>
+'''
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    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="openai/gpt-oss-20b")
+LICENSE = """
+<p/>
+---
+Built with Gemma-3-TAIDE-12b-Chat
+"""
 
-    messages = [{"role": "system", "content": system_message}]
+css = """
+h1 {
+  text-align: center;
+  display: block;
+}
+#duplicate-button {
+  margin: auto;
+  color: white;
+  background: #1565c0;
+  border-radius: 100vh;
+}
+"""
 
-    messages.extend(history)
 
-    messages.append({"role": "user", "content": message})
+def chat(message: str,
+              history: list,
+              temperature: float,
+              max_new_tokens: int
+             ) -> str:
+    """
+    Generate a streaming response using the llama3-8b model.
+    """
+    try:
+        messages = []
+        for user, assistant in history:
+            messages.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+        messages.append({"role": "user", "content": message})
 
-    response = ""
+        response = litellm.completion(
+            model="openai/Gemma-3-TAIDE-12b-Chat", # tells litellm to call the model via the Responses API
+            messages=messages,
+            max_completion_tokens=max_new_tokens,
+            temperature=temperature,
+            stream=True,
 
-    for message 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
+        )
+        output = []
+        for part in response:
+            content = part.choices[0].delta.content or ""
+            output.append(content)
+            yield "".join(output)
+    except Exception as e:
+        yield f"生成過程中發生錯誤: {str(e)}"
 
-        response += token
-        yield response
 
+# Gradio block
+chatbot = gr.Chatbot(height=450, label='Gradio ChatInterface')
 
-"""
-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 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)",
-        ),
-    ],
-)
+with gr.Blocks(fill_height=True, css=css) as demo:
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
+    gr.ChatInterface(
+        fn=chat,
+        chatbot=chatbot,
+        fill_height=True,
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
+        additional_inputs=[
+            gr.Slider(minimum=0,
+                      maximum=1,
+                      step=0.1,
+                      value=0.95,
+                      label="Temperature",
+                      render=False),
+            gr.Slider(minimum=128,
+                      maximum=131584,
+                      step=1,
+                      value=512,
+                      label="Max new tokens",
+                      render=False),
+        ],
+        examples=[
+            ['請以以下內容為基礎，寫一篇文章：撰寫一篇作文，題目為《一張舊照片》，內容要求為：選擇一張令你印象深刻的照片，說明令你印象深刻的原因，並描述照片中的影像及背後的故事。記錄成長的過程、與他人的情景、環境變遷和美麗的景色。'],
+            ['請以品牌經理的身份，給廣告公司的創意總監寫一封信，提出對於新產品廣告宣傳活動的創意建議。'],
+            ['以下提供英文內容，請幫我翻譯成中文。Dongshan coffee is famous for its unique position, and the constant refinement of production methods. The flavor is admired by many caffeine afficionados.'],
+        ],
+        cache_examples=False,
+    )
 
+    gr.Markdown(LICENSE)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(server_name='0.0.0.0')