🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
update readme
gongjy97886fef2ee7
diff --git a/README.md b/README.mdindex f80047a..825e46d 100644--- a/README.md+++ b/README.md@@ -255,7 +255,7 @@ print(torch.cuda.is_available())### 2.数据下载-从下文提供的[数据集下载链接](https://www.modelscope.cn/datasets/gongjy/minimind-dataset/files)+从下文提供的[数据集下载链接](https://www.modelscope.cn/datasets/gongjy/minimind_dataset/files)下载需要的数据文件放到`./dataset`目录下<details style="color:rgb(128,128,128)">@@ -476,7 +476,7 @@ quality(当然也还不算high,提升数据质量无止尽)。> [!NOTE]> 2025-02-05后,开源MiniMind最终训练所用的所有数据集,因此无需再自行预处理大规模数据集,避免重复性的数据处理工作。-MiniMind训练数据集 ([ModelScope](https://www.modelscope.cn/datasets/gongjy/minimind-dataset/files) | [HuggingFace](https://huggingface.co/datasets/jingyaogong/minimind_dataset/tree/main))+MiniMind训练数据集 ([ModelScope](https://www.modelscope.cn/datasets/gongjy/minimind_dataset/files) | [HuggingFace](https://huggingface.co/datasets/jingyaogong/minimind_dataset/tree/main))> 无需全部clone,可单独下载所需的文件diff --git a/README_en.md b/README_en.mdindex 0fd3460..48b4e6a 100644--- a/README_en.md+++ b/README_en.md@@ -270,7 +270,7 @@ for guidance.### 2. Data DownloadDownload the required data files from-the [dataset download link](https://www.modelscope.cn/datasets/gongjy/minimind-dataset/files) and place them in+the [dataset download link](https://www.modelscope.cn/datasets/gongjy/minimind_dataset/files) and place them inthe `./dataset` directory.<details style="color:rgb(128,128,128)">@@ -516,7 +516,7 @@ Big respect!MiniMind Training Datasets are available for download from:-Dataset ([ModelScope](https://www.modelscope.cn/datasets/gongjy/minimind-dataset/files) | [HuggingFace](https://huggingface.co/datasets/jingyaogong/minimind_dataset/tree/main))+Dataset ([ModelScope](https://www.modelscope.cn/datasets/gongjy/minimind_dataset/files) | [HuggingFace](https://huggingface.co/datasets/jingyaogong/minimind_dataset/tree/main))> You don’t need to clone everything, just download the necessary files.