Update app.py

app.py

@@ -6,11 +6,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 import gradio as gr
 from threading import Thread
 
-MODEL_LIST = ["meta-llama/Meta-Llama-3.1-8B-Instruct"]
+MODEL_LIST = ["CohereForAI/aya-expanse-8b"]
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
-MODEL = "ehristoforu/mllama-3.1-8b-instruct"
+MODEL = "CohereForAI/aya-expanse-8b"
 
-TITLE = "<h1><center>ehristoforu/mllama-3.1-8b-instruct</center></h1>"
+TITLE = "<h1><center>aya-expanse-8b</center></h1>"
 
 PLACEHOLDER = """
 <center>
@@ -83,7 +83,7 @@ def stream_chat(
         top_k = top_k,
         temperature = temperature,
         repetition_penalty=penalty,
-        eos_token_id=128009,
+        eos_token_id=255001,
         streamer=streamer,
     )
 
@@ -110,9 +110,7 @@ with gr.Blocks(css=CSS, theme="soft") as demo:
         additional_inputs=[
             gr.Textbox(
                 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.
+                You are a helpful assistant.
                 """,
                 label="System Prompt",
                 lines=5,