Update app.py

app.py

@@ -6,13 +6,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 import gradio as gr
 from threading import Thread
 
-MODEL_LIST = ["meta-llama/Meta-Llama-3.1-405B-Instruct"]
+MODEL_LIST = ["meta-llama/Meta-Llama-3.1-8B-Instruct"]
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
-MODEL = os.environ.get("MODEL_ID")
 
-print(MODEL)
-
-TITLE = "<h1><center>Meta-Llama3.1-405B</center></h1>"
+TITLE = "<h1><center>Meta-Llama3.1-8B</center></h1>"
 
 PLACEHOLDER = """
 <center>
@@ -41,9 +38,9 @@ quantization_config = BitsAndBytesConfig(
     bnb_4bit_use_double_quant=True,
     bnb_4bit_quant_type= "nf4")
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL)
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
 model = AutoModelForCausalLM.from_pretrained(
-    MODEL,
+    "meta-llama/Meta-Llama-3.1-8B-Instruct",
     torch_dtype=torch.bfloat16,
     device_map="auto",
     quantization_config=quantization_config)