diff --git a/README.md b/README.md
index d458d5b..2e8d614 100644
--- a/README.md
+++ b/README.md
@@ -178,7 +178,7 @@ print(torch.cuda.is_available())
 **3.1 预训练（学图像描述）**
 
 ```bash
-python train_pretrain_vlm.py --epochs 4
+bash scripts/pretrain_vlm.sh
 ```
 
 > 执行预训练，得到 `pretrain_vlm_*.pth` 作为预训练的输出权重（其中*为模型的dimension，默认为512）
@@ -187,7 +187,7 @@ python train_pretrain_vlm.py --epochs 4
 **3.2 监督微调（学看图对话方式）**
 
 ```bash
-python train_sft_vlm.py --epochs 4
+bash scripts/sft_vlm.sh
 ```
 
 > 执行监督微调，得到 `sft_vlm_*.pth` 作为指令微调的输出权重
diff --git a/README_en.md b/README_en.md
index 8c16e68..e3dbd53 100644
--- a/README_en.md
+++ b/README_en.md
@@ -189,7 +189,7 @@ skipping the pretrain training step and proceed directly to SFT training.
 **3.1 Pretraining (Learning image description)**
 
 ```bash
-python train_pretrain_vlm.py --epochs 4
+bash scripts/pretrain_vlm.sh
 ```
 
 > Run pretraining to get `pretrain_vlm_*.pth` as the pretrained model's output weights (* represents the model
@@ -198,7 +198,7 @@ python train_pretrain_vlm.py --epochs 4
 **3.2 Supervised Fine-Tuning (Learning image-caption dialogue style)**
 
 ```bash
-python train_sft_vlm.py --epochs 4
+bash scripts/sft_vlm.sh
 ```
 
 > Perform supervised fine-tuning to get `sft_vlm_*.pth` as the output weights for the fine-tuned model.
diff --git a/scripts/pretrain_vlm.sh b/scripts/pretrain_vlm.sh
new file mode 100644
index 0000000..67e5a4f
--- /dev/null
+++ b/scripts/pretrain_vlm.sh
@@ -0,0 +1,27 @@
+#!/bin/bash
+
+# 设置运行脚本的参数
+python train_pretrain_vlm.py \
+    --out_dir="out" \
+    --epochs=4 \
+    --batch_size=16 \
+    --learning_rate=0.0004 \
+    --device="cuda:0" \
+    --dtype="bfloat16" \
+    # --use_wandb \ # 如果使用wandb，请取消注释
+    --wandb_project="MiniMind-V" \
+    --num_workers=8 \
+    --data_path="./dataset/pretrain_data.jsonl" \
+    --images_path="./dataset/pretrain_images" \
+    # --ddp \ # 如果使用DDP分布式训练，请取消注释
+    --accumulation_steps=1 \
+    --grad_clip=1.0 \
+    --warmup_iters=0 \
+    --log_interval=100 \
+    --save_interval=100 \
+    --local_rank=-1 \
+    # 模型参数
+    --dim=512 \
+    --n_layers=8 \
+    --max_seq_len=640 \
+    --use_moe=False
diff --git a/scripts/sft_vlm.sh b/scripts/sft_vlm.sh
new file mode 100644
index 0000000..f7d3b31
--- /dev/null
+++ b/scripts/sft_vlm.sh
@@ -0,0 +1,27 @@
+#!/bin/bash
+
+# 设置运行脚本的参数
+python train_sft_vlm.py \
+    --out_dir="out" \
+    --epochs=6 \
+    --batch_size=8 \
+    --learning_rate=0.000001 \
+    --device="cuda:0" \
+    --dtype="bfloat16" \
+    # --use_wandb \ # 如果使用wandb，请取消注释
+    --wandb_project="MiniMind-V" \
+    --num_workers=8 \
+    --data_path="./dataset/sft_data.jsonl" \
+    --images_path="./dataset/sft_images" \
+    # --ddp \ # 如果使用DDP分布式训练，请取消注释
+    --accumulation_steps=1 \
+    --grad_clip=1.0 \
+    --warmup_iters=0 \
+    --log_interval=10 \
+    --save_interval=10 \
+    --local_rank=-1 \
+    # 模型参数
+    --dim=512 \
+    --n_layers=8 \
+    --max_seq_len=1536 \
+    --use_moe=False
diff --git a/train_pretrain_vlm.py b/train_pretrain_vlm.py
index 0bc7766..220940c 100644
--- a/train_pretrain_vlm.py
+++ b/train_pretrain_vlm.py
@@ -104,8 +104,8 @@ def init_model(model_config: VLMConfig):
     # 加载纯语言模型权重
     ckp = f'./out/lm_{model_config.dim}{moe_path}.pth'
     model = MiniMindVLM(model_config)
-    state_dict = torch.load(ckp, map_location=args.device)
-    model.load_state_dict(state_dict, strict=False)
+    # state_dict = torch.load(ckp, map_location=args.device)
+    # model.load_state_dict(state_dict, strict=False)
 
     # 冻结除 vision_proj 外的所有参数
     for name, param in model.named_parameters():
@@ -147,7 +147,7 @@ def init_distributed_mode():
     parser.add_argument("--use_wandb", default=False, action="store_true")
     parser.add_argument("--wandb_project", type=str, default="MiniMind-V")
     parser.add_argument("--num_workers", type=int, default=8)
-    parser.add_argument("--data_path", type=str, default="./dataset/pretrain_vlm_data.jsonl")
+    parser.add_argument("--data_path", type=str, default="./dataset/pretrain_data.jsonl")
     parser.add_argument("--images_path", type=str, default="./dataset/pretrain_images")
     parser.add_argument("--ddp", action="store_true")
     parser.add_argument("--accumulation_steps", type=int, default=1)
diff --git a/train_sft_vlm.py b/train_sft_vlm.py
index ea33c1a..f847300 100644
--- a/train_sft_vlm.py
+++ b/train_sft_vlm.py
@@ -137,7 +137,7 @@ def init_distributed_mode():
     parser.add_argument("--use_wandb", default=False, action="store_true")
     parser.add_argument("--wandb_project", type=str, default="MiniMind-V")
     parser.add_argument("--num_workers", type=int, default=8)
-    parser.add_argument("--data_path", type=str, default="./dataset/sft_vlm_data.jsonl")
+    parser.add_argument("--data_path", type=str, default="./dataset/sft_data.jsonl")
     parser.add_argument("--images_path", type=str, default="./dataset/sft_images")
     parser.add_argument("--ddp", action="store_true")
     parser.add_argument("--accumulation_steps", type=int, default=1)