diff --git a/data/dataset_info.json b/data/dataset_info.json
index 01f4db21..ceb81379 100644
--- a/data/dataset_info.json
+++ b/data/dataset_info.json
@@ -129,7 +129,6 @@
   },
   "firefly": {
     "hf_hub_url": "YeungNLP/firefly-train-1.1M",
-    "ms_hub_url": "AI-ModelScope/firefly-train-1.1M",
     "columns": {
       "prompt": "input",
       "response": "target"
diff --git a/src/llmtuner/data/loader.py b/src/llmtuner/data/loader.py
index 41c12422..7bd52caa 100644
--- a/src/llmtuner/data/loader.py
+++ b/src/llmtuner/data/loader.py
@@ -58,6 +58,11 @@ def get_dataset(
             dataset = MsDataset.load(
                 dataset_name=data_path,
                 subset_name=data_name,
+                split=data_args.split,
+                data_files=data_files,
+                cache_dir=model_args.cache_dir,
+                token=model_args.ms_hub_token,
+                streaming=(data_args.streaming and (dataset_attr.load_from != "file")),
             ).to_hf_dataset()
         else:
             dataset = load_dataset(
diff --git a/src/llmtuner/hparams/model_args.py b/src/llmtuner/hparams/model_args.py
index ebf6cafa..c5819cea 100644
--- a/src/llmtuner/hparams/model_args.py
+++ b/src/llmtuner/hparams/model_args.py
@@ -59,6 +59,10 @@ class ModelArguments:
         default=None,
         metadata={"help": "Auth token to log in with Hugging Face Hub."}
     )
+    ms_hub_token: Optional[str] = field(
+        default=None,
+        metadata={"help": "Auth token to log in with ModelScope Hub."}
+    )
 
     def __post_init__(self):
         self.compute_dtype = None