From b50ca5cafaa907c43b059383657c929a937e366d Mon Sep 17 00:00:00 2001
From: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Date: Tue, 18 Feb 2025 17:25:09 +0800
Subject: [PATCH] [data] add r1 distill dataset (#6983)

Former-commit-id: 1da5ee4edaa3896593b9cae488f0ac5917c3243e
---
 README.md              |  4 +++-
 README_zh.md           |  4 +++-
 data/dataset_info.json | 30 ++++++++++++++++++++++++------
 3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 6dfcf186..c4cc8a2c 100644
--- a/README.md
+++ b/README.md
@@ -348,7 +348,9 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 - [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
 - [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
 - [OpenO1-SFT (en&zh)](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)
-- [Open Thoughts (en)](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k)
+- [Open-Thoughts (en)](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k)
+- [Open-R1-Math (en)](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k)
+- [Chinese-DeepSeek-R1-Distill (zh)](https://huggingface.co/datasets/Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT)
 - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
 - [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
 - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
diff --git a/README_zh.md b/README_zh.md
index 06c58ffb..17ba8789 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -350,7 +350,9 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 - [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
 - [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
 - [OpenO1-SFT (en&zh)](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)
-- [Open Thoughts (en)](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k)
+- [Open-Thoughts (en)](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k)
+- [Open-R1-Math (en)](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k)
+- [Chinese-DeepSeek-R1-Distill (zh)](https://huggingface.co/datasets/Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT)
 - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
 - [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
 - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
diff --git a/data/dataset_info.json b/data/dataset_info.json
index 627eb355..7aaee14f 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -319,19 +319,37 @@
     }
   },
   "open_thoughts": {
-    "hf_hub_url": "open-thoughts/OpenThoughts-114k",
+    "hf_hub_url": "llamafactory/OpenThoughts-114k",
     "formatting": "sharegpt",
     "columns": {
-      "messages": "conversations",
-      "system": "system"
+      "messages": "messages"
     },
     "tags": {
-      "role_tag": "from",
-      "content_tag": "value",
+      "role_tag": "role",
+      "content_tag": "content",
       "user_tag": "user",
-      "assistant_tag": "assistant"
+      "assistant_tag": "assistant",
+      "system_tag": "system"
     }
   },
+  "open_r1_math": {
+    "hf_hub_url": "llamafactory/OpenR1-Math-94k",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "messages"
+    },
+    "tags": {
+      "role_tag": "role",
+      "content_tag": "content",
+      "user_tag": "user",
+      "assistant_tag": "assistant",
+      "system_tag": "system"
+    }
+  },
+  "chinese_r1_distill": {
+    "hf_hub_url": "Congliu/Chinese-DeepSeek-R1-Distill-data-110k-SFT",
+    "ms_hub_url": "liucong/Chinese-DeepSeek-R1-Distill-data-110k-SFT"
+  },
   "llava_1k_en": {
     "hf_hub_url": "BUAADreamer/llava-en-zh-2k",
     "subset": "en",