diff --git a/src/llamafactory/model/model_utils/misc.py b/src/llamafactory/model/model_utils/misc.py
index 000a1399..4883fa23 100644
--- a/src/llamafactory/model/model_utils/misc.py
+++ b/src/llamafactory/model/model_utils/misc.py
@@ -34,7 +34,7 @@ def find_all_linear_modules(model: "PreTrainedModel", freeze_vision_tower: bool)
         forbidden_modules.add("output_layer")
     elif model_type == "internlm2":
         forbidden_modules.add("output")
-    elif model_type in ["idefics2", "llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
+    elif model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
         forbidden_modules.add("multi_modal_projector")
     elif model_type == "qwen2_vl":
         forbidden_modules.add("merger")