From d925ecae1b30686a37b6bc15fac25655377696b5 Mon Sep 17 00:00:00 2001
From: hiyouga <hiyouga@buaa.edu.cn>
Date: Mon, 18 Dec 2023 19:09:31 +0800
Subject: [PATCH] add models

Former-commit-id: 3a4728557304996bcbe58d7d6380beead7c63c70
---
 data/README.md                   | 5 +++--
 data/README_zh.md                | 5 +++--
 src/llmtuner/extras/constants.py | 6 +++++-
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/data/README.md b/data/README.md
index 50adbcdb..7e56aa30 100644
--- a/data/README.md
+++ b/data/README.md
@@ -2,8 +2,9 @@ If you are using a custom dataset, please provide your dataset definition in the
 
 ```json
 "dataset_name": {
-  "hf_hub_url": "the name of the dataset repository on the Hugging Face hub. (if specified, ignore below 3 arguments)",
-  "script_url": "the name of the directory containing a dataset loading script. (if specified, ignore below 2 arguments)",
+  "hf_hub_url": "the name of the dataset repository on the Hugging Face hub. (if specified, ignore script_url and file_name)",
+  "ms_hub_url": "the name of the dataset repository on the ModelScope hub. (if specified, ignore script_url and file_name)",
+  "script_url": "the name of the directory containing a dataset loading script. (if specified, ignore file_name)",
   "file_name": "the name of the dataset file in this directory. (required if above are not specified)",
   "file_sha1": "the SHA-1 hash value of the dataset file. (optional, does not affect training)",
   "subset": "the name of the subset. (optional, default: None)",
diff --git a/data/README_zh.md b/data/README_zh.md
index 135a3b29..cb867a5b 100644
--- a/data/README_zh.md
+++ b/data/README_zh.md
@@ -2,8 +2,9 @@
 
 ```json
 "数据集名称": {
-  "hf_hub_url": "Hugging Face 的仓库地址（若指定，则忽略下列三个参数）",
-  "script_url": "包含数据加载脚本的本地文件夹名称（若指定，则忽略下列两个参数）",
+  "hf_hub_url": "Hugging Face 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
+  "ms_hub_url": "ModelScope 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
+  "script_url": "包含数据加载脚本的本地文件夹名称（若指定，则忽略 file_name）",
   "file_name": "该目录下数据集文件的名称（若上述参数未指定，则此项必需）",
   "file_sha1": "数据集文件的 SHA-1 哈希值（可选，留空不影响训练）",
   "subset": "数据集子集的名称（可选，默认：None）",
diff --git a/src/llmtuner/extras/constants.py b/src/llmtuner/extras/constants.py
index 478a7f99..8e72fc12 100644
--- a/src/llmtuner/extras/constants.py
+++ b/src/llmtuner/extras/constants.py
@@ -431,9 +431,13 @@ register_model_group(
 
 register_model_group(
     models={
-        "Phi1.5-1.3B": {
+        "Phi-1.5-1.3B": {
             DownloadSource.DEFAULT: "microsoft/phi-1_5",
             DownloadSource.MODELSCOPE: "allspace/PHI_1-5"
+        },
+        "Phi-2-2.7B": {
+            DownloadSource.DEFAULT: "microsoft/phi-2",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/phi-2"
         }
     },
     module="Wqkv"