Update app.py

app.py

@@ -15,7 +15,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
 
 if torch.cuda.is_available():
-    model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+    model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
 style = "<style>.user-message,.system-message{display:flex;margin:10px}.user-message .message-content{background-color:#c2e3f7;color:#000}.system-message .message-content{background-color:#f5f5f5;color:#000}.message-content{padding:10px;border-radius:10px;max-width:70%;word-wrap:break-word}.container{display:flex;justify-content:space-between}.column{width:48%}</style>"
@@ -70,7 +70,7 @@ chat_interface = ChatInterface(
     max_turns=10,
     repo_id="llm-human-feedback-collector-chat-interface-kto",
     chatbot=gr.Chatbot(
-        height=450, label="Meta-Llama-3-8B-Instruct", show_share_button=True
+        height=450, label="Meta-Llama-3.1-8B-Instruct", show_share_button=True
     ),
     css=style,
     cache_examples=False,