Update app.py

app.py

@@ -37,7 +37,7 @@ if not torch.cuda.is_available():
 
 if torch.cuda.is_available():
     # model_id = "meta-llama/Llama-2-13b-chat-hf"
-    model_id = "meta-llama/Meta-Llama-3-70B-Instruct"
+    model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False