From 4b108654bdb0c5379e9d1bcfa18a4efdaf7d60ad Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Wed, 5 Feb 2025 06:32:51 -0800 Subject: [PATCH] Update rl.py --- unsloth/models/rl.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index 932a29f78a..2282e8b313 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -43,8 +43,7 @@ def PatchRL(FastLanguageModel): FastLanguageModel.for_inference(unwrapped_model) yield unwrapped_model # Return back to training mode - FastLanguageModel.for_training (model) - yield model + FastLanguageModel.for_training(model) pass import trl.trainer