From ba2760dc6ac8bad16d43bbdc623dd5e0f15d3304 Mon Sep 17 00:00:00 2001
From: u010280923 <xinlu.nlp@foxmail.com>
Date: Fri, 17 Mar 2023 17:39:01 +0800
Subject: [PATCH] update readme.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 244ecf6..94f50da 100644
--- a/README.md
+++ b/README.md
@@ -77,7 +77,7 @@ python train_rm.py  --load_model "./out_sft/rwkv-190.pth" --wandb "" --proj_dir
 ### PPO Model (Reinforcement learning from Human Feedback)
 
 ```
-python train_rm.py  --load_sft_model "./out_sft/rwkv-190.pth" --load_rm_model "./out_rm/rm-2.pth" --wandb "" \
+python train_ppo.py  --load_sft_model "./out_sft/rwkv-190.pth" --load_rm_model "./out_rm/rm-2.pth" --wandb "" \
 --proj_dir "out_rlhf" \
 --data_file "data/rm_mock_data.csv" --data_type "utf-8" --vocab_size 50277 \
 --ctx_len 1024 --epoch_steps 200 --epoch_count 1000 --epoch_begin 0 --epoch_save 2 \
-- 
GitLab