diff --git a/src/transformers/models/mega/modeling_mega.py b/src/transformers/models/mega/modeling_mega.py
index 98914b439c18d5..494fff11b73f52 100644
--- a/src/transformers/models/mega/modeling_mega.py
+++ b/src/transformers/models/mega/modeling_mega.py
@@ -1743,7 +1743,7 @@ def forward(
         >>> config = AutoConfig.from_pretrained("mnaylor/mega-base-wikitext")
         >>> config.is_decoder = True
         >>> config.bidirectional = False
-        >>> model = MegaForCausalLM.from_pretrained("mnaylor/mega-base-wikitext", config=config)
+        >>> model = MegaForCausalLM.from_pretrained("mnaylor/mega-base-wikitext", config=config, ignore_mismatched_sizes=True)
 
         >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
         >>> outputs = model(**inputs)