Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,435 @@
+Tencent is pleased to support the open source community by making WeMM-Embedding-2B available.
+
+Copyright (C) 2026 Tencent.  All rights reserved. 
+
+The open-source software and/or models included in this distribution may have been modified by Tencent (“Tencent Modifications”). All Tencent Modifications are Copyright (C) Tencent.
+
+WeMM-Embedding-2B is licensed under Apache-2.0, except for the third-party components listed below, which remain licensed under their respective original terms. WeMM-Embedding-2B does not impose any additional restrictions beyond those specified in the original licenses of these third-party components. Users are required to comply with all applicable terms and conditions of the original licenses and to ensure that the use of these third-party components conforms to all relevant laws and regulations.
+
+For the avoidance of doubt, WeMM-Embedding-2B refers to code, parameters, and weights made publicly available by Tencent in accordance with Apache-2.0. 
+
+Terms of Apache-2.0:
+--------------------------------------------------------------------
+Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   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.
+
+
+Dependencies and Licenses:
+
+This open-source project, WeMM-Embedding-2B, builds upon the following open-source models and/or software components, each of which remains licensed under its original license. Certain models or software may include modifications made by Tencent (“Tencent Modifications”), which are Copyright (C) Tencent.
+
+In case you believe there have been errors in the attribution below, you may submit the concerns to us for review and correction.
+
+
+Open Source Model Licensed under the  Apache-2.0:
+--------------------------------------------------------------------
+1. Qwen3.5-2B
+Copyright 2026 Alibaba Cloud
+Please note this model has been modified by Tencent in this distribution.
+
+ 
+
+Terms of the  Apache-2.0：
+--------------------------------------------------------------------
+Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   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.
+
+

README.md

@@ -0,0 +1,139 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model:
+- Qwen/Qwen3.5-2B
+pipeline_tag: feature-extraction
+tags:
+- multimodal-embedding
+- text-embedding
+- image-embedding
+- video-embedding
+- mrl
+---
+
+# WeMM-Embedding-2B
+
+WeMM-Embedding-2B is a universal multimodal embedding model built on Qwen3.5. It accepts text, images, videos, visual documents, and interleaved multimodal inputs, and returns a 2,048-dimensional L2-normalized embedding. Audio input is not supported.
+
+## Installation
+
+```bash
+pip install torch transformers==5.2.0 "qwen-vl-utils[decord]==0.0.14" \
+  sentence-transformers==5.7.0 "accelerate>=1.1.0"
+```
+
+## Transformers
+
+```python
+import torch
+from qwen_vl_utils import process_vision_info
+from transformers import AutoModel, AutoProcessor
+
+model_id = "tencent/WeMM-Embedding-2B"
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModel.from_pretrained(
+    model_id, trust_remote_code=True, dtype=torch.bfloat16
+).cuda().eval()
+
+messages = [{"role": "user", "content": [
+    {"type": "image", "image": "/path/to/image.jpg"},
+    {"type": "video", "video": "/path/to/video.mp4"},
+    {"type": "text", "text": "This can be any text input."},
+]}]
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=False
+)
+images, videos, video_kwargs = process_vision_info(
+    messages,
+    image_patch_size=16,
+    return_video_kwargs=True,
+    return_video_metadata=True,
+)
+if videos is not None:
+    videos, video_metadata = zip(*videos)
+    videos, video_metadata = list(videos), list(video_metadata)
+else:
+    video_metadata = None
+inputs = processor(
+    text=text,
+    images=images,
+    videos=videos,
+    video_metadata=video_metadata,
+    return_tensors="pt",
+    **video_kwargs,
+).to("cuda")
+
+with torch.inference_mode():
+    embedding = model.embedding(**inputs)
+```
+
+Use any subset of the content items to encode text, image, or video independently.
+
+## Sentence Transformers
+
+```python
+from wemm_sentence_transformers import load_wemm_sentence_transformer
+
+model_id = "tencent/WeMM-Embedding-2B"
+model = load_wemm_sentence_transformer(model_id, device="cuda:0")
+inputs = [
+    "A dog is running on a beach.",
+    {"image": "/path/to/image.jpg", "text": "Represent this image."},
+    {"video": "/path/to/video.mp4", "text": "Represent this video."},
+]
+embeddings = model.encode(
+    inputs,
+    batch_size=1,
+    truncate_dim=256,
+    normalize_embeddings=True,
+)
+```
+
+
+## Matryoshka Embeddings
+
+```python
+embedding_256 = torch.nn.functional.normalize(embedding[..., :256], dim=-1)
+```
+
+Use a dimension listed in `model.config.matryoshka_dimensions`. On MMEB-v2, 256-dimensional embeddings retain 98.7% of the full-dimensional image and video performance.
+
+## Serving
+
+vLLM `0.27.0`:
+
+```bash
+MODEL_PATH=/path/to/WeMM-Embedding-2B
+vllm serve "$MODEL_PATH" \
+  --runner pooling \
+  --chat-template "$MODEL_PATH/embedding_chat_template.jinja"
+```
+
+SGLang `0.5.9`:
+
+```bash
+MODEL_PATH=/path/to/WeMM-Embedding-2B
+python patch_sglang_video.py
+python -m sglang.launch_server \
+  --model-path "$MODEL_PATH" \
+  --is-embedding \
+  --enable-precise-embedding-interpolation
+```
+
+## Citation
+
+```bibtex
+@techreport{wemm_embedding_2026,
+  title       = {WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report},
+  author      = {{WeChat Vision}},
+  institution = {Tencent Inc.},
+  year        = {2026}
+}
+```
+
+## License
+
+WeMM-Embedding-2B, including the code, model parameters, and weights made publicly
+available by Tencent, is licensed under the [Apache License 2.0](https://huggingface.co/tencent/WeMM-Embedding-2B/blob/main/LICENSE).
+Third-party components remain subject to their respective original licenses.

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,113 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 16,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 8,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248078
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "auto_map": {
+    "AutoModel": "modeling_wemm_embedding.WeMMEmbedding",
+    "AutoModelForCausalLM": "modeling_wemm_embedding.WeMMEmbedding"
+  },
+  "matryoshka_dimensions": [
+    64,
+    128,
+    256,
+    512,
+    1024,
+    2048
+  ]
+}

embedding_chat_template.jinja

@@ -0,0 +1,28 @@
+{# Direct-tokenization template for vLLM 0.27 embedding requests.
+   Qwen's processor post-processor removes the role newline before images,
+   keeps it before text/video, and appends <embedding> without a preceding
+   newline. vLLM 0.27 adds each frame's vision boundaries itself, so video
+   uses a bare <video_pad> placeholder. #}
+{%- for message in messages %}
+{{- '<|im_start|>' + message.role }}
+{%- if message.content is string %}
+{{- '\n' + message.content }}
+{%- else %}
+{%- for item in message.content %}
+{%- if item.type in ['image', 'image_url'] or 'image' in item or 'image_url' in item %}
+{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+{%- elif item.type in ['video', 'video_url'] or 'video' in item or 'video_url' in item %}
+{{- '\n<|video_pad|>' }}
+{%- elif item.type == 'text' or 'text' in item %}
+{{- ('\n' if loop.first else '') + item.text }}
+{%- else %}
+{{- raise_exception('Unsupported embedding content type') }}
+{%- endif %}
+{%- endfor %}
+{%- endif %}
+{{- '<|im_end|>' }}
+{%- if not loop.last %}
+{{- '\n' }}
+{%- endif %}
+{%- endfor %}
+{{- '<embedding>' }}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a1ad752808c26965aa97d37bf4a9bca71d838513f41e83790cb1e71cac6e59
+size 5441695216

modeling_wemm_embedding.py

@@ -0,0 +1,29 @@
+import torch
+import torch.nn.functional as F
+from transformers import Qwen3_5ForConditionalGeneration
+
+
+class WeMMEmbedding(Qwen3_5ForConditionalGeneration):
+    def embedding(self, input_ids=None, attention_mask=None, **kwargs):
+        outputs = self.model(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            **kwargs
+        )
+        
+        last_hidden_state = outputs.last_hidden_state
+
+        if attention_mask is not None:
+            eos_positions = attention_mask.sum(dim=1) - 1
+        else:
+            eos_positions = torch.full((last_hidden_state.shape[0],), last_hidden_state.shape[1] - 1, device=last_hidden_state.device)
+
+        eos_positions = eos_positions.clamp(min=0)
+        
+        batch_indices = torch.arange(last_hidden_state.size(0), device=last_hidden_state.device)
+        
+        embeddings = last_hidden_state[batch_indices, eos_positions]
+        
+        embeddings = F.normalize(embeddings, dim=-1)
+        
+        return embeddings

patch_sglang_video.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+"""Align SGLang 0.5.9 video preprocessing with WeMM-Embedding."""
+
+import importlib.metadata
+import py_compile
+import shutil
+from pathlib import Path
+
+import sglang
+
+
+EXPECTED_VERSION = "0.5.9"
+REPLACEMENTS = (
+    (
+        "IMAGE_FACTOR = 28",
+        "IMAGE_FACTOR = 32  # patch_size=16 * spatial_merge_size=2",
+    ),
+    (
+        "    idx = np.linspace(0, total_frames - 1, num=nframes, dtype=np.int64)",
+        "    idx = torch.linspace(0, total_frames - 1, nframes).round().long().cpu().numpy()",
+    ),
+    (
+        """    video = torchvision.transforms.functional.resize(
+        video,
+        [resized_height, resized_width],
+        interpolation=InterpolationMode.BILINEAR,
+    )
+""",
+        """    video = torchvision.transforms.functional.resize(
+        video,
+        [resized_height, resized_width],
+        interpolation=InterpolationMode.BICUBIC,
+        antialias=True,
+    ).float()
+""",
+    ),
+)
+
+
+def main() -> None:
+    version = importlib.metadata.version("sglang")
+    if version != EXPECTED_VERSION:
+        raise RuntimeError(f"Expected sglang=={EXPECTED_VERSION}, found {version}")
+
+    path = (
+        Path(sglang.__file__).resolve().parent
+        / "srt"
+        / "multimodal"
+        / "processors"
+        / "qwen_vl.py"
+    )
+    text = path.read_text(encoding="utf-8")
+    if all(new in text for _, new in REPLACEMENTS):
+        print("SGLang video preprocessing is ready.")
+        return
+
+    updated = text
+    for old, new in REPLACEMENTS:
+        if updated.count(old) != 1:
+            raise RuntimeError(f"Unexpected SGLang source: {old.splitlines()[0]}")
+        updated = updated.replace(old, new, 1)
+
+    backup = path.with_suffix(path.suffix + ".original")
+    if not backup.exists():
+        shutil.copy2(path, backup)
+    path.write_text(updated, encoding="utf-8")
+    py_compile.compile(str(path), doraise=True)
+    print("SGLang video preprocessing is ready.")
+
+
+if __name__ == "__main__":
+    main()
+

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 234881024,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e444c744512f423da4c8443c47c21e22ff76056ba4e9796a81c04c13a9daf0
+size 19990378

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

wemm_sentence_transformers.py

@@ -0,0 +1,198 @@
+#!/usr/bin/env python3
+"""Sentence-Transformers adapter for WeMM-Embedding."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+import torch
+from qwen_vl_utils import process_vision_info
+from sentence_transformers import SentenceTransformer
+from sentence_transformers.sentence_transformer.modules import InputModule
+from transformers import AutoModel, AutoProcessor
+
+
+def _as_messages(
+    value: Any,
+    prompt: str | None = None,
+) -> list[dict[str, Any]]:
+    if isinstance(value, str):
+        text = f"{prompt or ''}{value}"
+        return [{"role": "user", "content": [{"type": "text", "text": text}]}]
+
+    if isinstance(value, list):
+        if not value or not all(
+            isinstance(message, dict) and "role" in message for message in value
+        ):
+            raise TypeError("A list input must be one chat-style conversation.")
+        messages = [dict(message) for message in value]
+        if prompt:
+            messages.insert(0, {"role": "user", "content": prompt})
+        return messages
+
+    if not isinstance(value, dict):
+        raise TypeError(
+            "Input must be text, a chat conversation, or a multimodal dict."
+        )
+    if "messages" in value:
+        return _as_messages(value["messages"], prompt=prompt)
+
+    content: list[dict[str, Any]] = []
+    for modality in ("image", "video"):
+        if value.get(modality) is not None:
+            content.append({"type": modality, modality: value[modality]})
+    if value.get("text") is not None:
+        content.append(
+            {"type": "text", "text": f"{prompt or ''}{value['text']}"}
+        )
+    elif prompt:
+        content.append({"type": "text", "text": prompt})
+    if not content:
+        raise ValueError("Input must contain text, image, or video.")
+    return [{"role": "user", "content": content}]
+
+
+class WeMMInputModule(InputModule):
+    config_keys = ["model_name_or_path"]
+    save_in_root = False
+
+    def __init__(
+        self,
+        model_name_or_path: str,
+        *,
+        device: str | torch.device | None = None,
+        **_: Any,
+    ) -> None:
+        super().__init__()
+        self.model_name_or_path = str(model_name_or_path)
+        self.processor = AutoProcessor.from_pretrained(
+            self.model_name_or_path,
+            trust_remote_code=True,
+        )
+        self.tokenizer = self.processor.tokenizer
+        self.tokenizer.padding_side = "right"
+        self.auto_model = AutoModel.from_pretrained(
+            self.model_name_or_path,
+            trust_remote_code=True,
+            dtype=torch.bfloat16,
+            device_map=device,
+            attn_implementation="sdpa",
+            experts_implementation="eager",
+        ).eval()
+        self.embedding_token_id = self.tokenizer.convert_tokens_to_ids(
+            "<embedding>"
+        )
+        text_config = getattr(
+            self.auto_model.config,
+            "text_config",
+            self.auto_model.config,
+        )
+        self.embedding_dimension = int(text_config.hidden_size)
+
+    @property
+    def modalities(self):
+        return [
+            "text",
+            "image",
+            "video",
+            "message",
+            ("image", "text"),
+            ("text", "video"),
+        ]
+
+    @property
+    def max_seq_length(self) -> int:
+        return int(self.tokenizer.model_max_length)
+
+    def preprocess(
+        self,
+        inputs: list[Any],
+        prompt: str | None = None,
+        **_: Any,
+    ) -> dict[str, torch.Tensor | Any]:
+        conversations = [
+            _as_messages(value, prompt=prompt)
+            for value in inputs
+        ]
+        prompts = [
+            self.processor.apply_chat_template(
+                messages,
+                tokenize=False,
+                add_generation_prompt=False,
+            )
+            for messages in conversations
+        ]
+        images, videos, video_kwargs = process_vision_info(
+            conversations,
+            image_patch_size=16,
+            return_video_kwargs=True,
+            return_video_metadata=True,
+        )
+        if videos is not None:
+            videos, video_metadata = zip(*videos)
+            videos, video_metadata = list(videos), list(video_metadata)
+        else:
+            video_metadata = None
+
+        features = self.processor(
+            text=prompts,
+            images=images,
+            videos=videos,
+            video_metadata=video_metadata,
+            padding=True,
+            return_tensors="pt",
+            **video_kwargs,
+        )
+        input_ids = features["input_ids"]
+        positions = features["attention_mask"].sum(dim=1) - 1
+        batch = torch.arange(input_ids.shape[0])
+        terminal_ids = input_ids[batch, positions]
+        if not torch.all(terminal_ids == self.embedding_token_id):
+            raise RuntimeError("Each input must end with <embedding>.")
+        features["modality"] = "message"
+        return dict(features)
+
+    def forward(
+        self,
+        features: dict[str, torch.Tensor | Any],
+        **_: Any,
+    ) -> dict[str, torch.Tensor | Any]:
+        model_inputs = {
+            key: value
+            for key, value in features.items()
+            if key != "modality"
+        }
+        inner = getattr(self.auto_model, "model", None)
+        if inner is not None and hasattr(inner, "rope_deltas"):
+            inner.rope_deltas = None
+        features["sentence_embedding"] = self.auto_model.embedding(
+            **model_inputs
+        ).float()
+        return features
+
+    def get_embedding_dimension(self) -> int:
+        return self.embedding_dimension
+
+    def save(
+        self,
+        output_path: str,
+        *args: Any,
+        safe_serialization: bool = True,
+        **kwargs: Any,
+    ) -> None:
+        del args, safe_serialization, kwargs
+        self.save_config(output_path)
+
+
+def load_wemm_sentence_transformer(
+    model_name_or_path: str | Path,
+    *,
+    device: str | torch.device = "cuda:0",
+) -> SentenceTransformer:
+    return SentenceTransformer(
+        modules=[WeMMInputModule(str(model_name_or_path), device=device)],
+        device=str(device),
+        similarity_fn_name="cosine",
+    )
+