From ed252565f9d7e36e1b9a9a7534c547616c5231a1 Mon Sep 17 00:00:00 2001
From: hiyouga <hiyouga@buaa.edu.cn>
Date: Wed, 26 Jul 2023 17:05:12 +0800
Subject: [PATCH] update dataset

Former-commit-id: 4a044aabbd19c92a9ae93c1c30536f5086fd47f9
---
 README.md                                 |  1 +
 README_zh.md                              |  1 +
 data/dataset_info.json                    | 14 ++++++++++++--
 data/refgpt_zh_50k_p1.json.REMOVED.git-id |  2 +-
 data/refgpt_zh_50k_p2.json.REMOVED.git-id |  2 +-
 5 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 675b0c7d..ec62a5a6 100644
--- a/README.md
+++ b/README.md
@@ -83,6 +83,7 @@
   - [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)
   - [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa)
diff --git a/README_zh.md b/README_zh.md
index bb9236a4..abf674bc 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -83,6 +83,7 @@
   - [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)
   - [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa)
diff --git a/data/dataset_info.json b/data/dataset_info.json
index f16d1d85..3a3b4e76 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -51,7 +51,7 @@
   },
   "refgpt_zh_p1": {
     "file_name": "refgpt_zh_50k_p1.json",
-    "file_sha1": "995043a909eed6693f850a96fccb4d3803f3ea5e",
+    "file_sha1": "b40f4f4d0ffacd16da7c275b056d5b6670021752",
     "columns": {
       "prompt": "instruction",
       "query": "input",
@@ -61,7 +61,17 @@
   },
   "refgpt_zh_p2": {
     "file_name": "refgpt_zh_50k_p2.json",
-    "file_sha1": "d9442d5c4541fe5489b5b571871fbe7595ee3809",
+    "file_sha1": "181f32b2c60264a29f81f59d3c76095793eae1b0",
+    "columns": {
+      "prompt": "instruction",
+      "query": "input",
+      "response": "output",
+      "history": "history"
+    }
+  },
+  "lima": {
+    "file_name": "lima.json",
+    "file_sha1": "9db59f6b7007dc4b17529fc63379b9cd61640f37",
     "columns": {
       "prompt": "instruction",
       "query": "input",
diff --git a/data/refgpt_zh_50k_p1.json.REMOVED.git-id b/data/refgpt_zh_50k_p1.json.REMOVED.git-id
index 9acdf2c3..3e8a9e41 100644
--- a/data/refgpt_zh_50k_p1.json.REMOVED.git-id
+++ b/data/refgpt_zh_50k_p1.json.REMOVED.git-id
@@ -1 +1 @@
-56405bb8f52727e52e99693739494b9b7b0d7ba6
\ No newline at end of file
+f967a4f6d04a11308a15524aa9a846a19a8d1e83
\ No newline at end of file
diff --git a/data/refgpt_zh_50k_p2.json.REMOVED.git-id b/data/refgpt_zh_50k_p2.json.REMOVED.git-id
index c7919c81..a6525b27 100644
--- a/data/refgpt_zh_50k_p2.json.REMOVED.git-id
+++ b/data/refgpt_zh_50k_p2.json.REMOVED.git-id
@@ -1 +1 @@
-fa935248a5d40d2bdd5649af99a72a754d40ae7a
\ No newline at end of file
+0a4f0d74fd1c5cab2eb6d84a3a3fe669847becd8
\ No newline at end of file