Update app.py

app.py

@@ -17,7 +17,8 @@ model_id = "vikhyatk/moondream2"
 revision = "2024-04-02"
 tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
 moondream = AutoModelForCausalLM.from_pretrained(
-    model_id, trust_remote_code=True, revision=revision
+    model_id, trust_remote_code=True, revision=revision,
+    attn_implementation="flash_attention_2"
 ).to(device=device, dtype=dtype)
 moondream.eval()