diff --git a/.gitignore b/.gitignore
index 035eaed..b2a3d2d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -6,4 +6,5 @@ docs-minimind-v/
 测试.py
 .venv
 model
-minimind-3v
\ No newline at end of file
+minimind-3v
+dataset
\ No newline at end of file
diff --git a/README.md b/README.md
index 111a662..d56676b 100644
--- a/README.md
+++ b/README.md
@@ -227,6 +227,11 @@ print(torch.cuda.is_available())
 
 快速开始时，直接从[数据集链接](https://huggingface.co/datasets/jingyaogong/minimind-v_dataset)下载 `sft_i2t.parquet`，并放到 `./dataset` 下即可。
 
+```bash
+# 完整下载
+hf download --repo-type dataset jingyaogong/minimind-v_dataset --local-dir dataset 
+```
+
 <details style="color:rgb(128,128,128)">
 <summary>注：数据集须知</summary>
 
diff --git a/trainer/train_pretrain_vlm.py b/trainer/train_pretrain_vlm.py
index 7f684c4..3904239 100644
--- a/trainer/train_pretrain_vlm.py
+++ b/trainer/train_pretrain_vlm.py
@@ -95,7 +95,7 @@ if __name__ == "__main__":
     parser.add_argument("--learning_rate", type=float, default=4e-4, help="初始学习率")
     parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu", help="训练设备")
     parser.add_argument("--dtype", type=str, default="bfloat16", help="混合精度类型")
-    parser.add_argument("--num_workers", type=int, default=8, help="数据加载线程数")
+    parser.add_argument("--num_workers", type=int, default=0 if sys.platform == 'win32' else 8, help="数据加载线程数")
     parser.add_argument("--accumulation_steps", type=int, default=1, help="梯度累积步数")
     parser.add_argument("--grad_clip", type=float, default=1.0, help="梯度裁剪阈值")
     parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")
diff --git a/trainer/train_sft_vlm.py b/trainer/train_sft_vlm.py
index 5ebef0e..c862ed6 100644
--- a/trainer/train_sft_vlm.py
+++ b/trainer/train_sft_vlm.py
@@ -95,7 +95,7 @@ if __name__ == "__main__":
     parser.add_argument("--learning_rate", type=float, default=5e-6, help="初始学习率")
     parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu", help="训练设备")
     parser.add_argument("--dtype", type=str, default="bfloat16", help="混合精度类型")
-    parser.add_argument("--num_workers", type=int, default=8, help="数据加载线程数")
+    parser.add_argument("--num_workers", type=int, default=0 if sys.platform == 'win32' else 8, help="数据加载线程数")
     parser.add_argument("--accumulation_steps", type=int, default=1, help="梯度累积步数")
     parser.add_argument("--grad_clip", type=float, default=1.0, help="梯度裁剪阈值")
     parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")