Update app.py

app.py

@@ -38,7 +38,7 @@ if not torch.cuda.is_available():
 
 if torch.cuda.is_available():
     model_id = "meta-llama/Llama-2-7b-chat-hf"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", use_flash_attention_2=True)
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", attn_implementation="flash_attention_2")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False