Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-
 def respond(
     message,
     history: list[dict[str, str]],
@@ -12,26 +11,27 @@ def respond(
     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
+    Função que envia mensagens para o modelo Meta-LLaMA 3.1 8B Instruct via Hugging Face Inference API.
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    # Inicializa o cliente Hugging Face com o modelo Meta-LLaMA 3.1 8B Instruct
+    client = InferenceClient(token=hf_token.token, model="meta-llama/Meta-Llama-3.1-8B-Instruct")
 
+    # Prepara mensagens no formato chat
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    for message in client.chat_completion(
+    # Streaming da resposta token por token
+    for message_chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
+        choices = message_chunk.choices
         token = ""
         if len(choices) and choices[0].delta.content:
             token = choices[0].delta.content
@@ -39,32 +39,23 @@ def respond(
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Cria interface de chat Gradio
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
+# Layout com login Hugging Face
 with gr.Blocks() as demo:
     with gr.Sidebar():
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()