From 344b9a36b2e0b60ee61fba171b35a391e3517fed Mon Sep 17 00:00:00 2001
From: hiyouga <467089858@qq.com>
Date: Tue, 18 Jun 2024 23:32:18 +0800
Subject: [PATCH] tiny fix

---
 Dockerfile             |  1 +
 README.md              |  4 ++--
 README_zh.md           |  4 ++--
 data/dataset_info.json | 33 ++++++++++++---------------------
 4 files changed, 17 insertions(+), 25 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 9c2f645c..61d58005 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -43,4 +43,5 @@ EXPOSE 7860
 # Expose port 8000 for the API service
 EXPOSE 8000
 
+# Launch LLaMA Board
 CMD [ "llamafactory-cli", "webui" ]
diff --git a/README.md b/README.md
index 2d95583b..0e8e55f7 100644
--- a/README.md
+++ b/README.md
@@ -260,6 +260,8 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 - [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
 - [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
 - [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)
 - [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)
@@ -270,8 +272,6 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t
 - [Booksum (de)](https://huggingface.co/datasets/mayflowergmbh/booksum_de)
 - [Airoboros (de)](https://huggingface.co/datasets/mayflowergmbh/airoboros-3.0_de)
 - [Ultrachat (de)](https://huggingface.co/datasets/mayflowergmbh/ultra-chat_de)
-- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
-- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
 
 </details>
 
diff --git a/README_zh.md b/README_zh.md
index ed5475d3..152cd6fa 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -260,6 +260,8 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 - [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction)
 - [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo)
 - [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)
 - [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)
@@ -270,8 +272,6 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 - [Booksum (de)](https://huggingface.co/datasets/mayflowergmbh/booksum_de)
 - [Airoboros (de)](https://huggingface.co/datasets/mayflowergmbh/airoboros-3.0_de)
 - [Ultrachat (de)](https://huggingface.co/datasets/mayflowergmbh/ultra-chat_de)
-- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub)
-- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
 
 </details>
 
diff --git a/data/dataset_info.json b/data/dataset_info.json
index e321196a..f8ffd407 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -252,6 +252,17 @@
     "hf_hub_url": "m-a-p/neo_sft_phase2",
     "formatting": "sharegpt"
   },
+  "magpie_pro_300k": {
+    "hf_hub_url": "Magpie-Align/Magpie-Pro-300K-Filtered",
+    "formatting": "sharegpt"
+  },
+  "web_instruct": {
+    "hf_hub_url": "TIGER-Lab/WebInstructSub",
+    "columns": {
+      "prompt": "question",
+      "response": "answer"
+    }
+  },
   "llava_1k_en": {
     "hf_hub_url": "BUAADreamer/llava-en-zh-2k",
     "subset": "en",
@@ -550,25 +561,5 @@
       "prompt": "content"
     },
     "folder": "python"
-  },
-  "Magpie-Pro-300K-Filtered": {
-    "hf_hub_url": "Magpie-Align/Magpie-Pro-300K-Filtered",
-    "columns": {
-      "messages": "conversations"
-    },
-    "tags": {
-      "role_tag": "from",
-      "content_tag": "value",
-      "user_tag": "human",
-      "assistant_tag": "gpt"
-    },
-    "formatting": "sharegpt"
-  },
-  "WebInstructSub": {
-    "hf_hub_url": "TIGER-Lab/WebInstructSub",
-    "columns": {
-      "prompt": "question",
-      "response": "answer"
-    }
   }
-}
+}
\ No newline at end of file