put the original code

app.py

@@ -1,26 +1,70 @@
 import gradio as gr
-from transformers import pipeline
-
-# Créer le générateur de texte avec un modèle public
-generator = pipeline("text-generation", model="gpt2")
-
-def respond(message, history):
-    history = history or []
-    # Ajouter le message utilisateur
-    history.append({"role": "user", "content": message})
-    # Générer une réponse
-    answer = generator(message, max_length=50, do_sample=True)[0]["generated_text"]
-    history.append({"role": "assistant", "content": answer})
-    # Vider la textbox
-    return "", history
-
-# Interface Gradio
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox(label="Message")
-    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+from huggingface_hub import InferenceClient
+
+
+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")
+
+    messages = [{"role": "system", "content": system_message}]
+
+    messages.extend(history)
+
+    messages.append({"role": "user", "content": message})
 
-demo.launch()
+    response = ""
+
+    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
+"""
+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() as demo:
+    with gr.Sidebar():
+        gr.LoginButton()
+    chatbot.render()
 
 
-# import gradio as gr
+if __name__ == "__main__":
+    demo.launch()

app_bad.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from transformers import pipeline
+
+# Créer le générateur de texte avec un modèle public
+generator = pipeline("text-generation", model="gpt2")
+
+def respond(message, history):
+    history = history or []
+    # Ajouter le message utilisateur
+    history.append({"role": "user", "content": message})
+    # Générer une réponse
+    answer = generator(message, max_length=50, do_sample=True)[0]["generated_text"]
+    history.append({"role": "assistant", "content": answer})
+    # Vider la textbox
+    return "", history
+
+# Interface Gradio
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Message")
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+demo.launch()
+
+
+# import gradio as gr