change example code's default to FA2

README.md

@@ -105,7 +105,7 @@ from transformers import AutoProcessor
 
 model_id = "microsoft/Phi-3-vision-128k-instruct" 
 
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", trust_remote_code=True, torch_dtype="auto", attn_implementation='eager') # use attn_implementation='flash_attention_2' to enable flash attention
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", trust_remote_code=True, torch_dtype="auto", attn_implementation='flash_attention_2') # use attn_implementation='eager' to disable flash attention
 
 processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)