From 58159fb9cf7f02f4d2db4509c28cdeec74bda162 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sun, 16 Feb 2025 18:27:04 -0800 Subject: [PATCH] Update rl_replacements.py --- unsloth/models/rl_replacements.py | 1 + 1 file changed, 1 insertion(+) diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index b91c808710..8e930261f6 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -202,6 +202,7 @@ grpo_compute_loss = RL_REPLACEMENTS["grpo_compute_loss"] RL_PRE_ITEMS["grpo_trainer"].append(inspect.getsource(grpo_compute_loss)) global INPUTS +INPUTS = None # Edit _get_per_token_logps to handle mixed precision def grpo_trainer_compute_loss(function_name, function):