fix #1784

Former-commit-id: 28d5de7e78

data/README.md

@@ -4,9 +4,10 @@ If you are using a custom dataset, please provide your dataset definition in the
 "dataset_name": {
   "hf_hub_url": "the name of the dataset repository on the Hugging Face hub. (if specified, ignore below 3 arguments)",
   "script_url": "the name of the directory containing a dataset loading script. (if specified, ignore below 2 arguments)",
-  "file_name": "the name of the dataset file in the this directory. (required if above are not specified)",
+  "file_name": "the name of the dataset file in this directory. (required if above are not specified)",
   "file_sha1": "the SHA-1 hash value of the dataset file. (optional, does not affect training)",
   "subset": "the name of the subset. (optional, default: None)",
+  "folder": "the name of the folder of the dataset repository on the Hugging Face hub. (optional, default: None)",
   "ranking": "whether the dataset is a preference dataset or not. (default: false)",
   "formatting": "the format of the dataset. (optional, default: alpaca, can be chosen from {alpaca, sharegpt})",
   "columns": {

data/README_zh.md

@@ -2,11 +2,12 @@
 
 ```json
 "数据集名称": {
-  "hf_hub_url": "Hugging Face 上的项目地址（若指定，则忽略下列三个参数）",
+  "hf_hub_url": "Hugging Face 的仓库地址（若指定，则忽略下列三个参数）",
   "script_url": "包含数据加载脚本的本地文件夹名称（若指定，则忽略下列两个参数）",
   "file_name": "该目录下数据集文件的名称（若上述参数未指定，则此项必需）",
-  "file_sha1": "数据集文件的SHA-1哈希值（可选，留空不影响训练）",
+  "file_sha1": "数据集文件的 SHA-1 哈希值（可选，留空不影响训练）",
   "subset": "数据集子集的名称（可选，默认：None）",
+  "folder": "Hugging Face 仓库的文件夹名称（可选，默认：None）",
   "ranking": "是否为偏好数据集（可选，默认：False）",
   "formatting": "数据集格式（可选，默认：alpaca，可以为 alpaca 或 sharegpt）",
   "columns": {

data/dataset_info.json

@@ -274,10 +274,11 @@
       "prompt": "content"
     }
   },
-  "starcoder": {
+  "starcoder_python": {
     "hf_hub_url": "bigcode/starcoderdata",
     "columns": {
       "prompt": "content"
-    }
+    },
+    "folder": "python"
   }
 }