Update app.py

app.py

@@ -1,70 +1,108 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-
 def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    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")
-
+    """ZeroGPU Optimized Chat - microsoft/DialoGPT-medium"""
+    client = InferenceClient(
+        token=hf_token.token, 
+        model="microsoft/DialoGPT-medium"
+    )
+    
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
-
+    
     response = ""
+    try:
+        for chunk in client.chat_completion(
+            messages, 
+            max_tokens=max_tokens,
+            stream=True, 
+            temperature=temperature, 
+            top_p=top_p,
+        ):
+            if chunk.choices and chunk.choices[0].delta.content:
+                token = chunk.choices[0].delta.content
+                response += token
+                yield response
+    except Exception:
+        yield "Error: Modelo no disponible. Verifica ZeroGPU."
 
-    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
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Configuración optimizada para ZeroGPU
 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.Textbox(
+            value="Eres un asistente útil y amigable.",
+            label="Mensaje del sistema",
+            max_lines=3
+        ),
+        gr.Slider(
+            minimum=1, 
+            maximum=256,  # Reducido para ZeroGPU
+            value=128, 
+            step=1, 
+            label="Tokens máximos"
+        ),
         gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
+            minimum=0.1, 
+            maximum=2.0, 
+            value=0.7, 
+            step=0.1, 
+            label="Temperatura"
+        ),
+        gr.Slider(
+            minimum=0.1, 
+            maximum=1.0, 
+            value=0.9, 
+            step=0.05, 
+            label="Top-p"
         ),
     ],
+    title="💬 Chat ZeroGPU",
+    description="Chat rápido con ZeroGPU • microsoft/DialoGPT-medium",
+    theme="soft"
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+# Layout optimizado para Spaces
+with gr.Blocks(
+    title="ZeroGPU Chat",
+    theme=gr.themes.Soft()
+) as demo:
+    gr.Markdown(
+        """
+        # 🚀 Chat ZeroGPU
+        **Rápido y gratuito** con GPU acelerada
+        
+        *Modelo:* microsoft/DialoGPT-medium
+        *Hardware:* ZeroGPU (A10G)
+        """
+    )
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            chatbot.render()
+        with gr.Column(scale=0.3):
+            gr.Markdown("### ⚙️ Configuración")
+            gr.Markdown("**ZeroGPU activo**")
+            gr.Markdown("**Tiempo respuesta:** <1s")
+    
+    gr.Markdown("***Creado para Hugging Face Spaces***")
 
 if __name__ == "__main__":
-    demo.launch(ssr_mode=False)
+    demo.launch(
+        ssr_mode=False,
+        show_api=False,
+        share=True,
+        server_name="0.0.0.0",
+        server_port=7860
+    )