add new model-like

docs/source/en/_toctree.yml

@@ -685,6 +685,8 @@
         title: DePlot
       - local: model_doc/donut
         title: Donut
+      - local: model_doc/efficientsam
+        title: EfficientSam
       - local: model_doc/flava
         title: FLAVA
       - local: model_doc/git

docs/source/en/model_doc/efficientsam.md

@@ -0,0 +1,57 @@
+<!--Copyright 2023 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.
+
+⚠️ Note that this file is in Markdown but contain specific syntax for our doc-builder (similar to MDX) that may not be
+rendered properly in your Markdown viewer.
+
+-->
+
+# EfficientSam
+
+## Overview
+
+The EfficientSam model was proposed in [<INSERT PAPER NAME HERE>](<INSERT PAPER LINK HERE>) by <INSERT AUTHORS HERE>.
+<INSERT SHORT SUMMARY HERE>
+
+The abstract from the paper is the following:
+
+*<INSERT PAPER ABSTRACT HERE>*
+
+Tips:
+
+<INSERT TIPS ABOUT MODEL HERE>
+
+This model was contributed by [INSERT YOUR HF USERNAME HERE](https://huggingface.co/<INSERT YOUR HF USERNAME HERE>).
+The original code can be found [here](<INSERT LINK TO GITHUB REPO HERE>).
+
+
+## EfficientSamConfig
+
+[[autodoc]] EfficientSamConfig
+
+## EfficientSamVisionConfig
+
+[[autodoc]] EfficientSamVisionConfig
+
+## EfficientSamMaskDecoderConfig
+
+[[autodoc]] EfficientSamMaskDecoderConfig
+
+## EfficientSamPromptEncoderConfig
+
+[[autodoc]] EfficientSamPromptEncoderConfig
+
+
+## EfficientSamModel
+
+[[autodoc]] EfficientSamModel
+    - forward
+

src/transformers/__init__.py

@@ -743,6 +743,14 @@
         "SamPromptEncoderConfig",
         "SamVisionConfig",
     ],
+    "models.efficientsam": [
+        "EFFICIENTSAM_PRETRAINED_CONFIG_ARCHIVE_MAP",
+        "EfficientSamConfig",
+        "EfficientSamMaskDecoderConfig",
+
+        "EfficientSamPromptEncoderConfig",
+        "EfficientSamVisionConfig",
+    ],
     "models.seamless_m4t": [
         "SEAMLESS_M4T_PRETRAINED_CONFIG_ARCHIVE_MAP",
         "SeamlessM4TConfig",
@@ -3085,6 +3093,13 @@
             "SamPreTrainedModel",
         ]
     )
+    _import_structure["models.efficientsam"].extend(
+        [
+            "EFFICIENTSAM_PRETRAINED_MODEL_ARCHIVE_LIST",
+            "EfficientSamModel",
+            "EfficientSamPreTrainedModel",
+        ]
+    )
     _import_structure["models.seamless_m4t"].extend(
         [
             "SEAMLESS_M4T_PRETRAINED_MODEL_ARCHIVE_LIST",
@@ -5404,6 +5419,14 @@
         SamPromptEncoderConfig,
         SamVisionConfig,
     )
+    from .models.efficientsam import (
+        EFFICIENTSAM_PRETRAINED_CONFIG_ARCHIVE_MAP,
+        EfficientSamConfig,
+        EfficientSamMaskDecoderConfig,
+
+        EfficientSamPromptEncoderConfig,
+        EfficientSamVisionConfig,
+    )
     from .models.seamless_m4t import (
         SEAMLESS_M4T_PRETRAINED_CONFIG_ARCHIVE_MAP,
         SeamlessM4TConfig,
@@ -7433,6 +7456,11 @@
             SamModel,
             SamPreTrainedModel,
         )
+        from .models.efficientsam import (
+            EFFICIENTSAM_PRETRAINED_MODEL_ARCHIVE_LIST,
+            EfficientSamModel,
+            EfficientSamPreTrainedModel,
+        )
 
         # PyTorch model imports
         from .models.seamless_m4t import (

src/transformers/models/__init__.py

@@ -187,6 +187,7 @@
     roformer,
     rwkv,
     sam,
+    efficientsam,
     seamless_m4t,
     seamless_m4t_v2,
     segformer,

src/transformers/models/auto/configuration_auto.py

@@ -194,6 +194,7 @@
         ("roformer", "RoFormerConfig"),
         ("rwkv", "RwkvConfig"),
         ("sam", "SamConfig"),
+        ("efficientsam", "EfficientSamConfig"),
         ("seamless_m4t", "SeamlessM4TConfig"),
         ("seamless_m4t_v2", "SeamlessM4Tv2Config"),
         ("segformer", "SegformerConfig"),
@@ -412,6 +413,7 @@
         ("roformer", "ROFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"),
         ("rwkv", "RWKV_PRETRAINED_CONFIG_ARCHIVE_MAP"),
         ("sam", "SAM_PRETRAINED_CONFIG_ARCHIVE_MAP"),
+        ("efficientsam", "EFFICIENTSAM_PRETRAINED_CONFIG_ARCHIVE_MAP"),
         ("seamless_m4t", "SEAMLESS_M4T_PRETRAINED_CONFIG_ARCHIVE_MAP"),
         ("seamless_m4t_v2", "SEAMLESS_M4T_V2_PRETRAINED_CONFIG_ARCHIVE_MAP"),
         ("segformer", "SEGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"),
@@ -656,6 +658,7 @@
         ("roformer", "RoFormer"),
         ("rwkv", "RWKV"),
         ("sam", "SAM"),
+        ("efficientsam", "EfficientEfficientSam"),
         ("seamless_m4t", "SeamlessM4T"),
         ("seamless_m4t_v2", "SeamlessM4Tv2"),
         ("segformer", "SegFormer"),

src/transformers/models/auto/image_processing_auto.py

@@ -96,6 +96,7 @@
         ("regnet", "ConvNextImageProcessor"),
         ("resnet", "ConvNextImageProcessor"),
         ("sam", "SamImageProcessor"),
+        ("efficientsam", "EfficientSamImageProcessor"),
         ("segformer", "SegformerImageProcessor"),
         ("swiftformer", "ViTImageProcessor"),
         ("swin", "ViTImageProcessor"),

src/transformers/models/auto/modeling_auto.py

@@ -187,6 +187,7 @@
         ("roformer", "RoFormerModel"),
         ("rwkv", "RwkvModel"),
         ("sam", "SamModel"),
+        ("efficientsam", "EfficientSamModel"),
         ("seamless_m4t", "SeamlessM4TModel"),
         ("seamless_m4t_v2", "SeamlessM4Tv2Model"),
         ("segformer", "SegformerModel"),
@@ -1124,6 +1125,7 @@
 MODEL_FOR_MASK_GENERATION_MAPPING_NAMES = OrderedDict(
     [
         ("sam", "SamModel"),
+        ("efficientsam", "EfficientSamModel"),
     ]
 )
 

src/transformers/models/auto/processing_auto.py

@@ -74,6 +74,7 @@
         ("pix2struct", "Pix2StructProcessor"),
         ("pop2piano", "Pop2PianoProcessor"),
         ("sam", "SamProcessor"),
+        ("efficientsam", "EfficientSamProcessor"),
         ("seamless_m4t", "SeamlessM4TProcessor"),
         ("sew", "Wav2Vec2Processor"),
         ("sew-d", "Wav2Vec2Processor"),

src/transformers/models/efficientsam/__init__.py

@@ -0,0 +1,65 @@
+# Copyright 2023 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 (
+    OptionalDependencyNotAvailable,
+    _LazyModule,
+    is_torch_available,
+)
+
+
+_import_structure = {
+    "configuration_efficientsam": [
+        "EFFICIENTSAM_PRETRAINED_CONFIG_ARCHIVE_MAP",
+        "EfficientSamConfig",
+        "EfficientSamMaskDecoderConfig",
+        "EfficientSamPromptEncoderConfig",
+        "EfficientSamVisionConfig",
+    ],
+}
+
+
+try:
+    if not is_torch_available():
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    pass
+else:
+    _import_structure["modeling_efficientsam"] = [
+        "EFFICIENTSAM_PRETRAINED_MODEL_ARCHIVE_LIST",
+        "EfficientSamModel",
+        "EfficientSamPreTrainedModel",
+    ]
+if TYPE_CHECKING:
+    from .configuration_efficientsam import (
+        EFFICIENTSAM_PRETRAINED_CONFIG_ARCHIVE_MAP,
+        EfficientSamConfig,
+        EfficientSamMaskDecoderConfig,
+        EfficientSamPromptEncoderConfig,
+        EfficientSamVisionConfig,
+    )
+
+    try:
+        if not is_torch_available():
+            raise OptionalDependencyNotAvailable()
+    except OptionalDependencyNotAvailable:
+        pass
+    else:
+        from .modeling_efficientsam import EFFICIENTSAM_PRETRAINED_MODEL_ARCHIVE_LIST, EfficientSamModel, EfficientSamPreTrainedModel
+
+else:
+    import sys
+
+    sys.modules[__name__] = _LazyModule(__name__, globals()["__file__"], _import_structure, module_spec=__spec__)