From 1cd0ea1f13d853d7ee6fa7ab60bc9bdc38f47144 Mon Sep 17 00:00:00 2001
From: hiyouga <hiyouga@buaa.edu.cn>
Date: Wed, 13 Sep 2023 22:30:14 +0800
Subject: [PATCH] add MathInstruct dataset

Former-commit-id: 026af87e7fce091a0cda1afd6df3d6ab6189de9a
---
 README.md              |  3 ++-
 README_zh.md           |  3 ++-
 data/dataset_info.json | 19 ++++++++++++++-----
 3 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index a3c2d81d..c9b51665 100644
--- a/README.md
+++ b/README.md
@@ -90,10 +90,11 @@
   - [BELLE Dialogue 0.4M (zh)](https://huggingface.co/datasets/BelleGroup/generated_chat_0.4M)
   - [BELLE School Math 0.25M (zh)](https://huggingface.co/datasets/BelleGroup/school_math_0.25M)
   - [BELLE Multiturn Chat 0.8M (zh)](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M)
-  - [Firefly 1.1M (zh)](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)
   - [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
   - [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)
   - [Alpaca CoT (multilingual)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)
+  - [MathInstruct (en)](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)
+  - [Firefly 1.1M (zh)](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)
   - [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)
diff --git a/README_zh.md b/README_zh.md
index f603780f..de9667e6 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -90,10 +90,11 @@
   - [BELLE Dialogue 0.4M (zh)](https://huggingface.co/datasets/BelleGroup/generated_chat_0.4M)
   - [BELLE School Math 0.25M (zh)](https://huggingface.co/datasets/BelleGroup/school_math_0.25M)
   - [BELLE Multiturn Chat 0.8M (zh)](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M)
-  - [Firefly 1.1M (zh)](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)
   - [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
   - [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)
   - [Alpaca CoT (multilingual)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)
+  - [MathInstruct (en)](https://huggingface.co/datasets/TIGER-Lab/MathInstruct)
+  - [Firefly 1.1M (zh)](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M)
   - [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)
diff --git a/data/dataset_info.json b/data/dataset_info.json
index a2a0899e..f30c422a 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -95,6 +95,12 @@
       "history": "history"
     }
   },
+  "codealpaca": {
+    "hf_hub_url": "sahil2801/CodeAlpaca-20k"
+  },
+  "alpaca_cot": {
+    "hf_hub_url": "QingyiSi/Alpaca-CoT"
+  },
   "firefly": {
     "hf_hub_url": "YeungNLP/firefly-train-1.1M",
     "columns": {
@@ -104,11 +110,14 @@
       "history": ""
     }
   },
-  "codealpaca": {
-    "hf_hub_url": "sahil2801/CodeAlpaca-20k"
-  },
-  "alpaca_cot": {
-    "hf_hub_url": "QingyiSi/Alpaca-CoT"
+  "mathinstruct": {
+    "hf_hub_url": "TIGER-Lab/MathInstruct",
+    "columns": {
+      "prompt": "instruction",
+      "query": "",
+      "response": "output",
+      "history": ""
+    }
   },
   "webqa": {
     "hf_hub_url": "suolyer/webqa",