From 1a969535e4adb9a237490392b2c447ecc40ba2d6 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Thu, 17 Jul 2025 06:26:10 -0700 Subject: [PATCH] Update rl_replacements.py --- unsloth/models/rl_replacements.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index 760bb336b1..dc1680a0af 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -249,7 +249,7 @@ def grpo_trainer__generate_and_score_completions(function_name, function): found = re.findall( r"(\n([\s]{1,})if self\.max_prompt_length is not None:.*?"\ r"\2if self\.use_vllm:)", - a, + function, flags = re.DOTALL | re.MULTILINE, ) if len(found) != 0: