Upload README.md with huggingface_hub

README.md

@@ -1,41 +1,26 @@
----
-dataset_info:
-  features:
-  - name: data_source
-    dtype: string
-  - name: prompt
-    list:
-    - name: content
-      dtype: string
-    - name: role
-      dtype: string
-  - name: ability
-    dtype: string
-  - name: reward_model
-    struct:
-    - name: ground_truth
-      dtype: string
-    - name: style
-      dtype: string
-  - name: extra_info
-    struct:
-    - name: instruction
-      dtype: string
-    - name: output
-      dtype: string
-    - name: split
-      dtype: string
-  - name: quality
-    dtype: bool
-  splits:
-  - name: train
-    num_bytes: 140630
-    num_examples: 19
-  download_size: 92560
-  dataset_size: 140630
-configs:
-- config_name: default
-  data_files:
-  - split: train
-    path: data/train-*
----
+
+标签: browse，think，search，summarize，answer
+格式：
+{
+  "data_source": "数据来源标识",
+  "prompt": [
+    {
+      "role": "system",
+      "content": "系统指令，包含可用工具描述和输出格式要求"
+    },
+    {
+      "role": "user",
+      "content": "用户查询或请求"
+    }
+  ],
+  "ability": "能力标签",
+  "reward_model": {
+    "ground_truth": "标准答案，通常包含<think>、<browse>、<search>、<summarize>、<answer>标签",
+    "style": "回答风格标签"
+  },
+  "extra_info": {
+    "instruction": "详细指令",
+    "output": "模型输出",
+    "split": "train"
+  }
+}