From 604f85487b46b3eb01b68cb2cc6535b7cb5527a7 Mon Sep 17 00:00:00 2001
From: codemayq <codingma@pku.edu.cn>
Date: Sun, 27 Aug 2023 20:35:32 +0800
Subject: [PATCH] add ad gen dataset

---
 README.md              |  1 +
 README_zh.md           |  1 +
 data/dataset_info.json | 10 ++++++++++
 3 files changed, 12 insertions(+)

diff --git a/README.md b/README.md
index 0db73b16..69dfe649 100644
--- a/README.md
+++ b/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)
diff --git a/README_zh.md b/README_zh.md
index ec4a524c..628a2b10 100644
--- a/README_zh.md
+++ b/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)
diff --git a/data/dataset_info.json b/data/dataset_info.json
index 5fd4fb1f..4ae75089 100644
--- a/data/dataset_info.json
+++ b/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",