diff --git a/src/transformers/models/afmoe/configuration_afmoe.py b/src/transformers/models/afmoe/configuration_afmoe.py
index 76336c07f486..3239e26f49ad 100644
--- a/src/transformers/models/afmoe/configuration_afmoe.py
+++ b/src/transformers/models/afmoe/configuration_afmoe.py
@@ -87,7 +87,7 @@ class AfmoeConfig(PreTrainedConfig):
     output_router_logits: bool = False
     global_attn_every_n_layers: int | None = 4
     sliding_window: int | None = 1024
-    layer_types: list | None = None
+    layer_types: list[str] | None = None
     attention_dropout: float | int | None = 0.0
     mup_enabled: bool | None = False
     eos_token_id: int | list[int] | None = None
diff --git a/src/transformers/models/llama4/configuration_llama4.py b/src/transformers/models/llama4/configuration_llama4.py
index 09547826685d..e7258ff0f33a 100644
--- a/src/transformers/models/llama4/configuration_llama4.py
+++ b/src/transformers/models/llama4/configuration_llama4.py
@@ -166,7 +166,7 @@ class Llama4TextConfig(PreTrainedConfig):
     no_rope_layers: list[int] | None = None
     no_rope_layer_interval: int = 4
     attention_chunk_size: int = 8192
-    layer_types: list[int] | None = None
+    layer_types: list[str] | None = None
     attn_temperature_tuning: bool = True
     floor_scale: int = 8192
     attn_scale: float = 0.1