From c75b5b83c4982a6da1512ad6f9cc4d98cc761094 Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Fri, 9 Aug 2024 20:28:55 +0800
Subject: [PATCH] add magpie ultra dataset

---
 README.md              | 1 +
 README_zh.md           | 1 +
 data/dataset_info.json | 7 +++++++
 3 files changed, 9 insertions(+)

diff --git a/README.md b/README.md
index f21e7403..418bfd35 100644
--- a/README.md
+++ b/README.md
@@ -265,6 +265,7 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 - [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2)
 - [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
 - [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
+- [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
 - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
 - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
 - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
diff --git a/README_zh.md b/README_zh.md
index e70d4e6a..c8ff7d81 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -265,6 +265,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 - [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2)
 - [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
 - [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
+- [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
 - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
 - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
 - [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
diff --git a/data/dataset_info.json b/data/dataset_info.json
index 23b7e5d8..b00456d2 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -266,6 +266,13 @@
     "hf_hub_url": "Magpie-Align/Magpie-Pro-300K-Filtered",
     "formatting": "sharegpt"
   },
+  "magpie_ultra": {
+    "hf_hub_url": "argilla/magpie-ultra-v0.1",
+    "columns": {
+      "prompt": "instruction",
+      "response": "response"
+    }
+  },
   "web_instruct": {
     "hf_hub_url": "TIGER-Lab/WebInstructSub",
     "columns": {