add ad gen dataset

README.md

@@ -105,6 +105,7 @@
   - [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa)
   - [UltraChat (en)](https://github.com/thunlp/UltraChat)
   - [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn)
+  - [Ad Gen (zh)](https://arxiv.org/abs/1908.06605)
 - For reward modeling or DPO training:
   - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
   - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)

README_zh.md

@@ -105,6 +105,7 @@
   - [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa)
   - [UltraChat (en)](https://github.com/thunlp/UltraChat)
   - [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn)
+  - [Ad Gen (zh)](https://arxiv.org/abs/1908.06605)
 - 用于奖励模型或 DPO 训练：
   - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
   - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)

data/dataset_info.json

@@ -154,6 +154,16 @@
     "hf_hub_url": "zxbsmk/webnovel_cn",
     "stage": "sft"
   },
+  "ad_gen": {
+    "hf_hub_url": "HasturOfficial/adgen",
+    "columns": {
+      "prompt": "content",
+      "query": "",
+      "response": "summary",
+      "history": ""
+    },
+    "stage": "sft"
+  },
   "comparison_gpt4_en": {
     "file_name": "comparison_gpt4_data_en.json",
     "file_sha1": "96fa18313544e22444fe20eead7754b17da452ae",