atualização

app.py

@@ -4,7 +4,10 @@ from huggingface_hub import InferenceClient
 """
 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("HuggingFaceH4/zephyr-7b-beta")
+#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+#client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct")
+#client = InferenceClient("microsoft/Phi-3.5-mini-instruct")
+client = InferenceClient("unsloth/Llama-3.2-1B-Instruct")
 
 
 def respond(
@@ -27,17 +30,17 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+
+    mensagens = client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    )
+    response = mensagens.choices[0].message.content
+
+    return response
 
-        response += token
-        yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -45,7 +48,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a friendly Chatbot. Your name is Juninho.", 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(