Add Janus Model

docs/source/en/_toctree.yml

@@ -888,6 +888,8 @@
         title: InstructBLIP
       - local: model_doc/instructblipvideo
         title: InstructBlipVideo
+      - local: model_doc/janus
+        title: Janus
       - local: model_doc/kosmos-2
         title: KOSMOS-2
       - local: model_doc/layoutlm

docs/source/en/model_doc/janus.md

@@ -0,0 +1,55 @@
+<!--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.
+
+⚠️ 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.
+
+-->
+
+# Janus
+
+# Janus
+
+# Janus
+
+# Janus
+
+# Janus
+
+# Janus
+
+# Janus
+
+## Overview
+
+The Janus 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>).
+
+
+## JanusConfig
+
+[[autodoc]] JanusConfig
+
+## JanusForConditionalGeneration
+
+[[autodoc]] JanusForConditionalGeneration
+    - forward

src/transformers/__init__.py

@@ -558,6 +558,10 @@
         "LlavaConfig",
         "LlavaProcessor",
     ],
+    "models.janus": [
+        "JanusConfig",
+
+    ],
     "models.llava_next": [
         "LlavaNextConfig",
         "LlavaNextProcessor",
@@ -2720,6 +2724,12 @@
             "LlavaPreTrainedModel",
         ]
     )
+    _import_structure["models.janus"].extend(
+        [
+            "JanusForConditionalGeneration",
+            "JanusPreTrainedModel",
+        ]
+    )
     _import_structure["models.llava_next"].extend(
         [
             "LlavaNextForConditionalGeneration",
@@ -5635,6 +5645,10 @@
         LlavaConfig,
         LlavaProcessor,
     )
+    from .models.janus import (
+        JanusConfig,
+
+    )
     from .models.llava_next import (
         LlavaNextConfig,
         LlavaNextProcessor,
@@ -7580,6 +7594,10 @@
             LlavaForConditionalGeneration,
             LlavaPreTrainedModel,
         )
+        from .models.janus import (
+            JanusForConditionalGeneration,
+            JanusPreTrainedModel,
+        )
         from .models.llava_next import (
             LlavaNextForConditionalGeneration,
             LlavaNextPreTrainedModel,

src/transformers/models/__init__.py

@@ -143,6 +143,7 @@
     lilt,
     llama,
     llava,
+    janus,
     llava_next,
     llava_next_video,
     llava_onevision,

src/transformers/models/auto/configuration_auto.py

@@ -164,6 +164,7 @@
         ("lilt", "LiltConfig"),
         ("llama", "LlamaConfig"),
         ("llava", "LlavaConfig"),
+        ("janus", "JanusConfig"),
         ("llava_next", "LlavaNextConfig"),
         ("llava_next_video", "LlavaNextVideoConfig"),
         ("llava_onevision", "LlavaOnevisionConfig"),
@@ -495,6 +496,7 @@
         ("llama2", "Llama2"),
         ("llama3", "Llama3"),
         ("llava", "LLaVa"),
+        ("janus", "Janus"),
         ("llava_next", "LLaVA-NeXT"),
         ("llava_next_video", "LLaVa-NeXT-Video"),
         ("llava_onevision", "LLaVA-Onevision"),

src/transformers/models/auto/modeling_auto.py

@@ -342,6 +342,7 @@
         ("idefics3", "Idefics3ForConditionalGeneration"),
         ("layoutlm", "LayoutLMForMaskedLM"),
         ("llava", "LlavaForConditionalGeneration"),
+        ("janus", "JanusForConditionalGeneration"),
         ("llava_next", "LlavaNextForConditionalGeneration"),
         ("llava_next_video", "LlavaNextVideoForConditionalGeneration"),
         ("llava_onevision", "LlavaOnevisionForConditionalGeneration"),
@@ -784,6 +785,7 @@
         ("instructblipvideo", "InstructBlipVideoForConditionalGeneration"),
         ("kosmos-2", "Kosmos2ForConditionalGeneration"),
         ("llava", "LlavaForConditionalGeneration"),
+        ("janus", "JanusForConditionalGeneration"),
         ("llava_next", "LlavaNextForConditionalGeneration"),
         ("llava_next_video", "LlavaNextVideoForConditionalGeneration"),
         ("llava_onevision", "LlavaOnevisionForConditionalGeneration"),
@@ -820,6 +822,7 @@
         ("instructblip", "InstructBlipForConditionalGeneration"),
         ("kosmos-2", "Kosmos2ForConditionalGeneration"),
         ("llava", "LlavaForConditionalGeneration"),
+        ("janus", "JanusForConditionalGeneration"),
         ("llava_next", "LlavaNextForConditionalGeneration"),
         ("llava_onevision", "LlavaOnevisionForConditionalGeneration"),
         ("mllama", "MllamaForConditionalGeneration"),

src/transformers/models/auto/processing_auto.py

@@ -76,6 +76,7 @@
         ("layoutlmv2", "LayoutLMv2Processor"),
         ("layoutlmv3", "LayoutLMv3Processor"),
         ("llava", "LlavaProcessor"),
+        ("janus", "JanusProcessor"),
         ("llava_next", "LlavaNextProcessor"),
         ("llava_next_video", "LlavaNextVideoProcessor"),
         ("llava_onevision", "LlavaOnevisionProcessor"),

src/transformers/models/auto/tokenization_auto.py

@@ -271,6 +271,7 @@
                 ),
             ),
             ("llava", ("LlamaTokenizer", "LlamaTokenizerFast" if is_tokenizers_available() else None)),
+            ("janus", ("LlamaTokenizer", "LlamaTokenizerFast" if is_tokenizers_available() else None)),
             ("llava_next", ("LlamaTokenizer", "LlamaTokenizerFast" if is_tokenizers_available() else None)),
             ("llava_next_video", ("LlamaTokenizer", "LlamaTokenizerFast" if is_tokenizers_available() else None)),
             ("llava_onevision", ("LlamaTokenizer", "LlamaTokenizerFast" if is_tokenizers_available() else None)),

src/transformers/models/janus/__init__.py

@@ -0,0 +1,27 @@
+# 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
+from ...utils.import_utils import define_import_structure
+
+
+if TYPE_CHECKING:
+    from .configuration_janus import *
+    from .modeling_janus import *
+else:
+    import sys
+
+    _file = globals()["__file__"]
+    sys.modules[__name__] = _LazyModule(__name__, _file, define_import_structure(_file), module_spec=__spec__)