[data] add coig-p dataset (#7657)

data/README.md

@@ -85,7 +85,7 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
 
 ### Pre-training Dataset
 
-- [Example dataset](c4_demo.json)
+- [Example dataset](c4_demo.jsonl)
 
 In pre-training, only the `text` column will be used for model learning.
 

data/README_zh.md

@@ -85,7 +85,7 @@
 
 ### 预训练数据集
 
-- [样例数据集](c4_demo.json)
+- [样例数据集](c4_demo.jsonl)
 
 在预训练时，只有 `text` 列中的内容会用于模型学习。
 

data/dataset_info.json

@@ -527,6 +527,16 @@
       "rejected": "rejected"
     }
   },
+  "coig_p": {
+    "hf_hub_url": "m-a-p/COIG-P",
+    "ranking": true,
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations",
+      "chosen": "chosen",
+      "rejected": "rejected"
+    }
+  },
   "rlhf_v": {
     "hf_hub_url": "llamafactory/RLHF-V",
     "ranking": true,
@@ -622,7 +632,7 @@
     }
   },
   "c4_demo": {
-    "file_name": "c4_demo.json",
+    "file_name": "c4_demo.jsonl",
     "columns": {
       "prompt": "text"
     }