update dataset

2025-12-14 10:56:56 +08:00 · 2023-07-26 17:05:12 +08:00
parent 00efa8a07f
commit f5c2ccdde4
6 changed files with 9659 additions and 3230 deletions
--- 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)
--- 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)
--- 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",
--- a/data/lima.json
+++ b/data/lima.json
--- a/data/refgpt_zh_50k_p1.json
+++ b/data/refgpt_zh_50k_p1.json
--- a/data/refgpt_zh_50k_p2.json
+++ b/data/refgpt_zh_50k_p2.json