[misc] update format (#7277)

src/llamafactory/data/processor/__init__.py

@@ -1,3 +1,17 @@
+# Copyright 2025 the LlamaFactory team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 from .feedback import FeedbackDatasetProcessor
 from .pairwise import PairwiseDatasetProcessor
 from .pretrain import PretrainDatasetProcessor

src/llamafactory/data/processor/feedback.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from collections import defaultdict
-from collections.abc import Sequence
 from typing import TYPE_CHECKING, Any, Optional
 
 from ...extras import logging
@@ -31,14 +30,14 @@ logger = logging.get_logger(__name__)
 class FeedbackDatasetProcessor(DatasetProcessor):
     def _encode_data_example(
         self,
-        prompt: Sequence[dict[str, str]],
-        response: Sequence[dict[str, str]],
-        kl_response: Sequence[dict[str, str]],
+        prompt: list[dict[str, str]],
+        response: list[dict[str, str]],
+        kl_response: list[dict[str, str]],
         system: Optional[str],
         tools: Optional[str],
-        images: Sequence["ImageInput"],
-        videos: Sequence["VideoInput"],
-        audios: Sequence["AudioInput"],
+        images: list["ImageInput"],
+        videos: list["VideoInput"],
+        audios: list["AudioInput"],
     ) -> tuple[list[int], list[int], list[int], list[int], bool]:
         if response[0]["content"]:  # desired example
             kto_tag = True

src/llamafactory/data/processor/pairwise.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from collections import defaultdict
-from collections.abc import Sequence
 from typing import TYPE_CHECKING, Any, Optional
 
 from ...extras import logging
@@ -31,13 +30,13 @@ logger = logging.get_logger(__name__)
 class PairwiseDatasetProcessor(DatasetProcessor):
     def _encode_data_example(
         self,
-        prompt: Sequence[dict[str, str]],
-        response: Sequence[dict[str, str]],
+        prompt: list[dict[str, str]],
+        response: list[dict[str, str]],
         system: Optional[str],
         tools: Optional[str],
-        images: Sequence["ImageInput"],
-        videos: Sequence["VideoInput"],
-        audios: Sequence["AudioInput"],
+        images: list["ImageInput"],
+        videos: list["VideoInput"],
+        audios: list["AudioInput"],
     ) -> tuple[list[int], list[int], list[int], list[int]]:
         chosen_messages = self.template.mm_plugin.process_messages(
             prompt + [response[0]], images, videos, audios, self.processor

src/llamafactory/data/processor/pretrain.py

@@ -1,4 +1,4 @@
-# Copyright 2024 HuggingFace Inc. and the LlamaFactory team.
+# Copyright 2025 HuggingFace Inc. and the LlamaFactory team.
 #
 # This code is inspired by the HuggingFace's transformers library.
 # https://github.com/huggingface/transformers/blob/v4.40.0/examples/pytorch/language-modeling/run_clm.py

src/llamafactory/data/processor/processor_utils.py

@@ -14,7 +14,6 @@
 
 import bisect
 from abc import ABC, abstractmethod
-from collections.abc import Sequence
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any, Optional
 
@@ -46,7 +45,7 @@ class DatasetProcessor(ABC):
         ...
 
 
-def search_for_fit(numbers: Sequence[int], capacity: int) -> int:
+def search_for_fit(numbers: list[int], capacity: int) -> int:
     r"""Find the index of largest number that fits into the knapsack with the given capacity."""
     index = bisect.bisect(numbers, capacity)
     return -1 if index == 0 else (index - 1)

src/llamafactory/data/processor/supervised.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from collections import defaultdict
-from collections.abc import Sequence
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any, Optional
 
@@ -33,13 +32,13 @@ logger = logging.get_logger(__name__)
 class SupervisedDatasetProcessor(DatasetProcessor):
     def _encode_data_example(
         self,
-        prompt: Sequence[dict[str, str]],
-        response: Sequence[dict[str, str]],
+        prompt: list[dict[str, str]],
+        response: list[dict[str, str]],
         system: Optional[str],
         tools: Optional[str],
-        images: Sequence["ImageInput"],
-        videos: Sequence["VideoInput"],
-        audios: Sequence["AudioInput"],
+        images: list["ImageInput"],
+        videos: list["VideoInput"],
+        audios: list["AudioInput"],
     ) -> tuple[list[int], list[int]]:
         messages = self.template.mm_plugin.process_messages(prompt + response, images, videos, audios, self.processor)
         input_ids, labels = self.template.mm_plugin.process_token_ids(

src/llamafactory/data/processor/unsupervised.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from collections import defaultdict
-from collections.abc import Sequence
 from typing import TYPE_CHECKING, Any, Optional
 
 from ...extras import logging
@@ -31,13 +30,13 @@ logger = logging.get_logger(__name__)
 class UnsupervisedDatasetProcessor(DatasetProcessor):
     def _encode_data_example(
         self,
-        prompt: Sequence[dict[str, str]],
-        response: Sequence[dict[str, str]],
+        prompt: list[dict[str, str]],
+        response: list[dict[str, str]],
         system: Optional[str],
         tools: Optional[str],
-        images: Sequence["ImageInput"],
-        videos: Sequence["VideoInput"],
-        audios: Sequence["AudioInput"],
+        images: list["ImageInput"],
+        videos: list["VideoInput"],
+        audios: list["AudioInput"],
     ) -> tuple[list[int], list[int]]:
         if len(response) == 1:
             messages = prompt + response