Fix

Author: lkhl

src/transformers/modeling_utils.py

@@ -220,7 +220,6 @@ def is_local_dist_rank_0():
     "qwen2vl",
     "qwen2_5_vl",
     "videollava",
-    "videollama3",
     "vipllava",
 ]
 

src/transformers/models/videollama3/__init__.py

@@ -1,3 +1,16 @@
+# Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# 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 typing import TYPE_CHECKING
 
 from ...utils import _LazyModule

src/transformers/models/videollama3/configuration_videollama3.py

@@ -4,8 +4,20 @@
 #             the file from the modular. If any change should be done, please apply the change to the
 #                          modular_videollama3.py file directly. One of our CI enforces this.
 #                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
-from transformers.configuration_utils import PretrainedConfig
-
+# Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# 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 ...configuration_utils import PretrainedConfig
 from ..auto import CONFIG_MAPPING, AutoConfig
 
 

src/transformers/models/videollama3/image_processing_videollama3.py

@@ -1,28 +1,43 @@
+# Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# 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.
 """Image processor class for VideoLLaMA3."""
 
 import math
 from typing import Optional, Union
 
 import numpy as np
 
-from transformers.feature_extraction_utils import BatchFeature
-from transformers.image_utils import (
+from ...feature_extraction_utils import BatchFeature
+from ...image_processing_utils import BaseImageProcessor
+from ...image_transforms import convert_to_rgb, resize, to_channel_dimension_format
+from ...image_utils import (
     IMAGENET_STANDARD_MEAN,
     IMAGENET_STANDARD_STD,
     ChannelDimension,
     ImageInput,
     PILImageResampling,
     get_image_size,
+    infer_channel_dimension_format,
+    is_scaled_image,
     make_flat_list_of_images,
+    make_list_of_images,
+    to_numpy_array,
     valid_images,
     validate_preprocess_arguments,
 )
-from transformers.utils import TensorType, logging
-from transformers.video_utils import VideoInput
-
-from ...image_processing_utils import BaseImageProcessor
-from ...image_transforms import convert_to_rgb, resize, to_channel_dimension_format
-from ...image_utils import infer_channel_dimension_format, is_scaled_image, make_list_of_images, to_numpy_array
+from ...utils import TensorType, logging
+from ...video_utils import VideoInput
 
 
 logger = logging.get_logger(__name__)

src/transformers/models/videollama3/image_processing_videollama3_fast.py

@@ -4,27 +4,43 @@
 #             the file from the modular. If any change should be done, please apply the change to the
 #                          modular_videollama3.py file directly. One of our CI enforces this.
 #                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+# Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# 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.
 import math
 from typing import Optional, Union
 
 import torch
 import torch.nn.functional as F
 
-from transformers.feature_extraction_utils import BatchFeature
-from transformers.image_processing_utils_fast import DefaultFastImageProcessorKwargs
-from transformers.image_utils import (
+from ...feature_extraction_utils import BatchFeature
+from ...image_processing_utils_fast import (
+    BaseImageProcessorFast,
+    DefaultFastImageProcessorKwargs,
+    group_images_by_shape,
+    reorder_images,
+)
+from ...image_utils import (
     IMAGENET_STANDARD_MEAN,
     IMAGENET_STANDARD_STD,
     ChannelDimension,
     ImageInput,
+    PILImageResampling,
     SizeDict,
 )
-from transformers.processing_utils import Unpack
-from transformers.utils import TensorType, auto_docstring, logging
-from transformers.video_utils import VideoInput, make_batched_videos
-
-from ...image_processing_utils_fast import BaseImageProcessorFast, group_images_by_shape, reorder_images
-from ...image_utils import PILImageResampling
+from ...processing_utils import Unpack
+from ...utils import TensorType, auto_docstring, logging
+from ...video_utils import VideoInput, make_batched_videos
 
 
 logger = logging.get_logger(__name__)