Update space

app.py

@@ -1,10 +1,8 @@
 import gradio as gr
 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("unsloth/Llama-3.2-3B-Instruct") 
+# Replace with your fine-tuned model endpoint
+client = InferenceClient("emeses/lab2_model")
 
 
 def respond(
@@ -27,6 +25,7 @@ def respond(
 
     response = ""
 
+    # Stream tokens from the model response
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,14 +34,11 @@ def respond(
         top_p=top_p,
     ):
         token = message.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
-"""
+# Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +55,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()