From d503093ec4c905878d26d389f1cd1f65dd476c42 Mon Sep 17 00:00:00 2001
From: jingyaogong <gongjy.cs@qq.com>
Date: Wed, 9 Apr 2025 16:56:57 +0800
Subject: [PATCH] update eval

---
 eval_model.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/eval_model.py b/eval_model.py
index 251dfc1..a031b52 100644
--- a/eval_model.py
+++ b/eval_model.py
@@ -16,7 +16,7 @@ def init_model(args):
     tokenizer = AutoTokenizer.from_pretrained('./model/minimind_tokenizer')
     if args.load == 0:
         moe_path = '_moe' if args.use_moe else ''
-        modes = {0: 'pretrain', 1: 'full_sft', 2: 'rlhf', 3: 'reason'}
+        modes = {0: 'pretrain', 1: 'full_sft', 2: 'rlhf', 3: 'reason', 4: 'grpo'}
         ckp = f'./{args.out_dir}/{modes[args.model_mode]}_{args.dim}{moe_path}.pth'
 
         model = MiniMindLM(LMConfig(
@@ -123,7 +123,7 @@ def main():
     parser.add_argument('--stream', default=True, type=bool)
     parser.add_argument('--load', default=0, type=int, help="0: 原生torch权重，1: transformers加载")
     parser.add_argument('--model_mode', default=1, type=int,
-                        help="0: 预训练模型，1: SFT-Chat模型，2: RLHF-Chat模型，3: Reason模型")
+                        help="0: 预训练模型，1: SFT-Chat模型，2: RLHF-Chat模型，3: Reason模型，4: RLAIF-Chat模型")
     args = parser.parse_args()
 
     model, tokenizer = init_model(args)
@@ -143,7 +143,7 @@ def main():
             messages,
             tokenize=False,
             add_generation_prompt=True
-        )[-args.max_seq_len + 1:] if args.model_mode != 0 else (tokenizer.bos_token + prompt)
+        )[-args.max_seq_len - 1:] if args.model_mode != 0 else (tokenizer.bos_token + prompt)
 
         answer = new_prompt
         with torch.no_grad():