From 165d823891dd5010437774bb952351d4e7d477c5 Mon Sep 17 00:00:00 2001 From: "hanluzhi0429@gmail.com" Date: Sun, 22 Jun 2025 23:31:24 +0800 Subject: [PATCH] [2025.06.22] add reward model PPO GRPO train code --- ...{step5_train_reward_model.py => step5.0_train_reward_model.py} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename src/{step5_train_reward_model.py => step5.0_train_reward_model.py} (100%) diff --git a/src/step5_train_reward_model.py b/src/step5.0_train_reward_model.py similarity index 100% rename from src/step5_train_reward_model.py rename to src/step5.0_train_reward_model.py