src/llamafactory/data/parser.py

@@ -15,7 +15,7 @@
 import json
 import os
 from dataclasses import dataclass
-from typing import Any, Literal, Optional, Union
+from typing import Any, Literal, Optional
 
 from huggingface_hub import hf_hub_download
 
@@ -90,14 +90,12 @@ class DatasetAttr:
                 self.set_attr(tag, attr["tags"])
 
 
-def get_dataset_list(dataset_names: Optional[list[str]], dataset_dir: Union[str, dict]) -> list["DatasetAttr"]:
+def get_dataset_list(dataset_names: Optional[list[str]], dataset_dir: str) -> list["DatasetAttr"]:
     r"""Get the attributes of the datasets."""
     if dataset_names is None:
         dataset_names = []
 
-    if isinstance(dataset_dir, dict):
-        dataset_info = dataset_dir
-    elif dataset_dir == "ONLINE":
+    if dataset_dir == "ONLINE":
         dataset_info = None
     else:
         if dataset_dir.startswith("REMOTE:"):

src/llamafactory/extras/constants.py

@@ -2755,14 +2755,6 @@ register_model_group(
             DownloadSource.DEFAULT: "Qwen/Qwen3-4B",
             DownloadSource.MODELSCOPE: "Qwen/Qwen3-4B",
         },
-        "Qwen3-4B-Instruct-2507": {
-            DownloadSource.DEFAULT: "Qwen/Qwen3-4B-Instruct-2507",
-            DownloadSource.MODELSCOPE: "Qwen/Qwen3-4B-Instruct-2507",
-        },
-        "Qwen3-4B-Thinking-2507": {
-            DownloadSource.DEFAULT: "Qwen/Qwen3-4B-Thinking-2507",
-            DownloadSource.MODELSCOPE: "Qwen/Qwen3-4B-Thinking-2507",
-        },
         "Qwen3-8B-Thinking": {
             DownloadSource.DEFAULT: "Qwen/Qwen3-8B",
             DownloadSource.MODELSCOPE: "Qwen/Qwen3-8B",

src/llamafactory/hparams/data_args.py

@@ -16,7 +16,7 @@
 # limitations under the License.
 
 from dataclasses import asdict, dataclass, field
-from typing import Any, Literal, Optional, Union
+from typing import Any, Literal, Optional
 
 
 @dataclass
@@ -35,7 +35,7 @@ class DataArguments:
         default=None,
         metadata={"help": "The name of dataset(s) to use for evaluation. Use commas to separate multiple datasets."},
     )
-    dataset_dir: Union[str, dict] = field(
+    dataset_dir: str = field(
         default="data",
         metadata={"help": "Path to the folder containing the datasets."},
     )