diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py
index 18103ca7eb..9fd9390a4b 100644
--- a/unsloth/models/rl.py
+++ b/unsloth/models/rl.py
@@ -1306,7 +1306,7 @@ def patch_trl_rl_trainers():
     import trl.trainer
 
     all_trainers = dir(trl.trainer)
-    all_trainers = [x for x in all_trainers if x.islower() and x.endswith("_trainer")]
+    all_trainers = [x for x in all_trainers if x.islower() and x.endswith("_trainer") and x != "base_trainer"]
     for trainer in all_trainers:
         _patch_trl_rl_trainers(trainer)
     return