Legacy tokenizer (#2465)

Author: SdeeRK

paddleformers/transformers/__init__.py

@@ -37,6 +37,12 @@
         "AddedToken",
         "normalize_chars",
         "tokenize_special_chars,convert_to_unicode,",
+        "PreTrainedTokenizer",
+    ],
+    "tokenizer_utils_base": [
+        "PaddingStrategy",
+        "TextInput",
+        "TensorType",
     ],
     "attention_utils": ["create_bigbird_rand_mask_idx_list"],
     "tensor_parallel_utils": [],
@@ -340,7 +346,6 @@
         tokenize_special_chars,
         convert_to_unicode,
     )
-    from .tokenizer_utils_fast import PretrainedTokenizerFast
     from .processing_utils import ProcessorMixin
     from .feature_extraction_utils import BatchFeature, FeatureExtractionMixin
     from .image_processing_utils import ImageProcessingMixin

paddleformers/transformers/image_utils.py

@@ -25,7 +25,7 @@
 import requests
 from packaging import version
 
-from .tokenizer_utils_base import ExplicitEnum
+from .tokenizer_utils import ExplicitEnum
 
 IMAGENET_DEFAULT_MEAN = [0.485, 0.456, 0.406]
 IMAGENET_DEFAULT_STD = [0.229, 0.224, 0.225]

paddleformers/transformers/legacy/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) 2025 PaddlePaddle Authors. 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.