Publish MADL model weights

.gitattributes

@@ -0,0 +1,4 @@
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+agent_a_qwen_lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,201 @@
+                                 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.

MANIFEST.json

@@ -0,0 +1,49 @@
+{
+  "format_version": "madl.weights.v1",
+  "base_model": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "external_weights_not_included": [
+    "SAM ViT-H (sam_vit_h_4b8939.pth)"
+  ],
+  "files": [
+    {
+      "path": "agent_a_qwen_lora/adapter_config.json",
+      "bytes": 3553,
+      "sha256": "64389a52b2f8ab288e51c135253a2e86144638bc88dda9f9bf9e00e951967f3d"
+    },
+    {
+      "path": "agent_a_qwen_lora/adapter_model.safetensors",
+      "bytes": 259096432,
+      "sha256": "fdf98c24a7ef5389b5eee3bdf94a05413d219bd7021ac6d291e1f60ade890e37"
+    },
+    {
+      "path": "agent_a_qwen_lora/chat_template.jinja",
+      "bytes": 1017,
+      "sha256": "a0bc6f6fc7a29a80017a433e8f03a1cc1236e838a944a2d034295a60c4f2fddb"
+    },
+    {
+      "path": "agent_a_qwen_lora/processor_config.json",
+      "bytes": 1424,
+      "sha256": "d2e174783f6eb77885c1c9b59a5739e540f64668cff3abe97df446fac96999c7"
+    },
+    {
+      "path": "agent_a_qwen_lora/tokenizer.json",
+      "bytes": 11421892,
+      "sha256": "3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8"
+    },
+    {
+      "path": "agent_a_qwen_lora/tokenizer_config.json",
+      "bytes": 735,
+      "sha256": "d64774ede2507fce562bb5a5287f5fb7ba0b71f83236fc877970fe90348bf9b3"
+    },
+    {
+      "path": "agent_b_dualstream/madl_agent_b_dualstream_v1.pt",
+      "bytes": 230858058,
+      "sha256": "65a96f53964a8370af0984ef915a6aac513742762b5f805e406bb6261838f10d"
+    },
+    {
+      "path": "agent_b_visual_ranker/madl_agent_b_visual_ranker_v1.pt",
+      "bytes": 111951107,
+      "sha256": "f7f210ca8cf0ad0686f2331b049f6662b919ea5f0912808279898d4cee23fc8c"
+    }
+  ]
+}

README.md

@@ -0,0 +1,103 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+datasets:
+  - Huang-yating/SID_Set
+language:
+  - en
+library_name: transformers
+pipeline_tag: image-classification
+tags:
+  - image-forensics
+  - image-manipulation-localization
+  - multi-agent
+  - qwen2.5-vl
+---
+
+# MADL model weights
+
+This repository is the weight companion for **MADL: Towards Dependable Image
+Forgery Detection via Multi-Agent Forensic Reasoning**. The executable code,
+configuration files, and evaluation scripts are distributed in the companion
+[GitHub code repository](https://github.com/shannima/MADL).
+
+Model repository: [moindy/MADL](https://huggingface.co/moindy/MADL).
+
+MADL produces one of three image-level labels—`real`, `synthetic`, or
+`tampered`—and returns a binary localization mask only for locally tampered
+images. The release contains the trainable components developed for MADL; it
+does not redistribute the Qwen base model or SAM ViT-H.
+
+## Files
+
+| Directory | Component | Purpose |
+|---|---|---|
+| `agent_a_qwen_lora/` | Agent A LoRA adapter | Adapts Qwen2.5-VL-7B-Instruct to three-class semantic verification and region proposals. |
+| `agent_b_dualstream/` | Agent B dual-stream checkpoint | RGB/SRM ConvNeXt-Tiny classifier and continuous manipulation heatmap. |
+| `agent_b_visual_ranker/` | Agent B visual-ranker checkpoint | Selects a final SAM candidate using RGB, mask, heatmap, and geometry evidence. |
+| `MANIFEST.json` | Integrity manifest | Records the byte size and SHA-256 of every released model artifact. |
+
+The dual-stream release checkpoint contains only the model state, architecture,
+class names, and a compact training summary. Optimizer state and local training
+paths were intentionally removed. The visual-ranker checkpoint uses the
+strict four-field runtime schema required by the companion loader.
+
+## External dependencies
+
+1. Download `Qwen/Qwen2.5-VL-7B-Instruct` through Transformers or the
+   Hugging Face Hub. PEFT reads this identifier from `adapter_config.json`.
+2. Download the official SAM ViT-H checkpoint
+   `sam_vit_h_4b8939.pth` from Meta's Segment Anything release.
+3. Place this repository under the runtime weight root and place SAM at
+   `external/sam_vit_h_4b8939.pth`, or override the relative paths in the MADL
+   YAML configuration.
+
+Expected layout:
+
+```text
+models/
+├── agent_a_qwen_lora/
+├── agent_b_dualstream/
+│   └── madl_agent_b_dualstream_v1.pt
+├── agent_b_visual_ranker/
+│   └── madl_agent_b_visual_ranker_v1.pt
+└── external/
+    └── sam_vit_h_4b8939.pth
+```
+
+Verify the files before inference:
+
+```bash
+python scripts/verify_weights.py /path/to/models
+```
+
+## Training data and evaluation scope
+
+The released components were trained for the SID-Set task, which distinguishes
+authentic, fully synthetic, and locally tampered images and provides masks for
+the locally tampered class. The release does not include SID-Set images. Users
+must obtain the dataset under its own terms.
+
+## Intended use
+
+The weights are intended for academic research on image forgery detection,
+localization, evidence interaction, and multi-agent forensic reasoning. They
+are not a substitute for human forensic examination and should not be used as
+the sole basis for legal, disciplinary, or content-removal decisions.
+
+## Limitations
+
+- Very small, fragmented, or weak-trace manipulations remain difficult.
+- Cross-dataset behavior has not been established by the final manuscript.
+- Multiple model calls increase latency and GPU memory requirements.
+- The natural-language field is a structured evidence trace; the release does
+  not claim that it has been independently evaluated as explanation quality.
+- Results depend on the exact Qwen, SAM, preprocessing, and threshold versions
+  documented by the companion code.
+
+## Licenses and attribution
+
+The released MADL code and original weight packaging are provided under
+Apache-2.0. Qwen2.5-VL, SAM, SID-Set, and other dependencies retain their own
+licenses and terms. The [code README](https://github.com/shannima/MADL#third-party-components)
+lists the relevant upstream projects. Dataset-derived use should preserve SID-Set attribution.

agent_a_qwen_lora/adapter_config.json

@@ -0,0 +1,129 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "model.visual.merger"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.11.mlp.up_proj",
+    "layers.26.mlp.down_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.24.mlp.gate_proj",
+    "layers.17.mlp.up_proj",
+    "layers.13.mlp.gate_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.8.mlp.up_proj",
+    "layers.25.mlp.up_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.7.mlp.up_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.25.mlp.down_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.26.mlp.up_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.17.mlp.down_proj",
+    "layers.19.mlp.down_proj",
+    "layers.22.mlp.up_proj",
+    "v_proj",
+    "layers.23.mlp.down_proj",
+    "layers.9.mlp.gate_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.6.mlp.up_proj",
+    "layers.18.mlp.down_proj",
+    "layers.18.mlp.up_proj",
+    "layers.3.mlp.down_proj",
+    "layers.3.mlp.up_proj",
+    "layers.20.mlp.down_proj",
+    "layers.14.mlp.up_proj",
+    "layers.16.mlp.down_proj",
+    "layers.2.mlp.up_proj",
+    "layers.1.mlp.down_proj",
+    "layers.23.mlp.gate_proj",
+    "layers.6.mlp.down_proj",
+    "layers.16.mlp.gate_proj",
+    "layers.24.mlp.up_proj",
+    "q_proj",
+    "layers.21.mlp.up_proj",
+    "layers.14.mlp.down_proj",
+    "layers.22.mlp.down_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.2.mlp.down_proj",
+    "layers.27.mlp.up_proj",
+    "layers.27.mlp.down_proj",
+    "layers.11.mlp.down_proj",
+    "layers.5.mlp.up_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.15.mlp.up_proj",
+    "layers.19.mlp.up_proj",
+    "layers.7.mlp.down_proj",
+    "layers.0.mlp.down_proj",
+    "layers.2.mlp.gate_proj",
+    "layers.9.mlp.up_proj",
+    "layers.13.mlp.up_proj",
+    "layers.24.mlp.down_proj",
+    "layers.12.mlp.up_proj",
+    "o_proj",
+    "layers.5.mlp.down_proj",
+    "layers.13.mlp.down_proj",
+    "layers.0.mlp.up_proj",
+    "layers.10.mlp.up_proj",
+    "layers.21.mlp.down_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.1.mlp.up_proj",
+    "layers.27.mlp.gate_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.12.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.8.mlp.down_proj",
+    "layers.10.mlp.down_proj",
+    "layers.23.mlp.up_proj",
+    "layers.16.mlp.up_proj",
+    "layers.4.mlp.down_proj",
+    "layers.26.mlp.gate_proj",
+    "k_proj",
+    "layers.15.mlp.down_proj",
+    "layers.20.mlp.up_proj",
+    "layers.4.mlp.up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

agent_a_qwen_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf98c24a7ef5389b5eee3bdf94a05413d219bd7021ac6d291e1f60ade890e37
+size 259096432

agent_a_qwen_lora/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

agent_a_qwen_lora/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 12845056,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

agent_a_qwen_lora/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

agent_a_qwen_lora/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

agent_b_dualstream/madl_agent_b_dualstream_v1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a96f53964a8370af0984ef915a6aac513742762b5f805e406bb6261838f10d
+size 230858058

agent_b_visual_ranker/madl_agent_b_visual_ranker_v1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f210ca8cf0ad0686f2331b049f6662b919ea5f0912808279898d4cee23fc8c
+size 111951107