Update app.py

app.py

@@ -8,9 +8,9 @@ from threading import Thread
 
 MODEL_LIST = ["meta-llama/Meta-Llama-3.1-8B-Instruct"]
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
-MODEL = os.environ.get("MODEL_ID")
+MODEL = "Skywork/Skywork-o1-Open-Llama-3.1-8B"
 
-TITLE = "<h1><center>Meta-Llama3.1-8B</center></h1>"
+TITLE = "<h1><center>Skywork-o1-Open-Llama-3.1-8B</center></h1>"
 
 PLACEHOLDER = """
 <center>
@@ -83,7 +83,7 @@ def stream_chat(
         top_k = top_k,
         temperature = temperature,
         repetition_penalty=penalty,
-        eos_token_id=[128001,128008,128009],
+        eos_token_id=128009,
         streamer=streamer,
     )
 
@@ -109,7 +109,11 @@ with gr.Blocks(css=CSS, theme="soft") as demo:
         additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
         additional_inputs=[
             gr.Textbox(
-                value="You are a helpful assistant",
+                value="""
+                You are Skywork-o1, a thinking model developed by Skywork AI, specializing in solving complex problems involving mathematics, coding, and logical reasoning through deep thought. 
+                When faced with a user's request, you first engage in a lengthy and in-depth thinking process to explore possible solutions to the problem. 
+                After completing your thoughts, you then provide a detailed explanation of the solution process in your response.
+                """,
                 label="System Prompt",
                 render=False,
             ),