From a50f74faa807e4d510762036052f34e5116cca56 Mon Sep 17 00:00:00 2001 From: pluesclues <136766175+pluesclues@users.noreply.github.com> Date: Thu, 5 Feb 2026 11:22:42 -0500 Subject: [PATCH] Update rl_replacements.py (#3990) --- 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 8208dc922a..410eee66e6 100755 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -459,7 +459,7 @@ def grpo_trainer__generate_and_score_completions(function_name, function): function = function.replace(string_to_find, replacement_string) - if trl_version >= Version("0.25.0"): + if trl_version >= Version("0.24.0"): # We replace the call using 'completions' with one using 'completions_text' string_to_find = " rewards_per_func = self._calculate_rewards(inputs, prompts, completions, completion_ids_list)" replacement_string = (