Add files using upload-large-folder tool

LICENSE

@@ -0,0 +1,210 @@
+Tencent is pleased to support the open source community by making Hy-Embodied-RxBrain-1.0. 
+
+Copyright (C) 2026 Tencent.  All rights reserved. 
+
+For the avoidance of doubt, Hy-Embodied-RxBrain-1.0 refers to the code and model parameter weights made publicly available by Tencent. 
+
+
+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 +1,196 @@
+---
+license: other
+language:
+- multilingual
+pipeline_tag: image-text-to-text
+tags:
+- hunyuan
+- hunyuan_vl_mot
+- unified_mot
+- vision-language
+- Embodied
+- image-to-text
+- any-to-any
+- MoT
+- flow-matching
+---
+
+<div align="center">
+<h1>RxBrain</h1>
+<p><b>Embodied Cognition Foundation Model with Joint Language–Visual Reasoning and Imagination</b></p>
+<p><i>Tencent Robotics X × Futian Laboratory × Tencent Hunyuan</i></p>
+
+<a href="https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0/blob/main/assets/RxBrain_v0.pdf"><img src="https://img.shields.io/badge/Paper-Report-red?logo=adobeacrobatreader" alt="Tech Report"></a>
+<a href="https://huggingface.co/tencent/Hy-Embodied-RxBrain-1.0"><img src="https://img.shields.io/badge/Models-HuggingFace-yellow?logo=huggingface" alt="Models"></a>
+<a href="https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0"><img src="https://img.shields.io/badge/GitHub-Repo-181717?logo=github&logoColor=white" alt="GitHub"></a>
+
+</div>
+
+<div align="center">
+<img src="https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0/blob/main/assets/teaser.png?raw=true" alt="RxBrain — capability overview" width="90%">
+</div>
+
+## 🔥 Updates
+
+  * **`[2026-07]`** 🎉 We release **Hy-Embodied-RxBrain-1.0** — the technical report, official inference code, and model weights.
+
+## 📖 Introduction
+
+**RxBrain** (`Hy-Embodied-RxBrain-1.0`) is a **unified multimodal foundation model for embodied cognition** — a single model that couples language reasoning with visual imagination to deliver three core capabilities:
+
+  * 🤖 **Embodied Understanding & Reasoning** — question answering and chain-of-thought over images and multi-frame video.
+  * 🔮 **World State Prediction** — imagine the near-future frames an action produces in the physical world.
+  * 🧩 **Joint Subgoal Planning** — decompose a task into steps, emitting for each step *both* the next action (language) *and* the goal image it should reach (vision).
+
+These capabilities are unified through **interleaved generation**: within a single autoregressive sequence RxBrain alternates reasoning text and flow-matched imagined frames — a learned `<Image>` token decides when to imagine — so an embodied plan couples *what to do* with *what the world should look like*, step by step.
+
+## ⭐️ Key Features
+
+  * 🧠 **Unified Mixture-of-Transformers (MoT):** A ~6.2B-parameter backbone with modality-specific pathways (text / vision / generation), so understanding and image synthesis share one autoregressive model instead of separate towers.
+  * 🎨 **Flow-Matching Image Head:** Imagined frames are produced by a flow-matching head decoding into a frozen **FLUX** VAE latent space, enabling text-to-image, multi-frame world-model rollout, and goal-image planning.
+  * 🔗 **Interleaved Reasoning + Imagination:** Text reasoning and generated frames are emitted in one sequence, coupling symbolic plans with visual goals.
+
+## 📅 Roadmap
+
+- [x] Transformers Inference (understanding + generation)
+- [ ] vLLM Inference
+- [ ] Fine-tuning Code
+- [ ] Online Gradio Demo
+
+## 🛠️ Dependencies and Installation
+
+### Prerequisites
+
+- 🖥️ **Operating System**: Linux (recommended)
+- 🐍 **Python**: 3.10+
+- ⚡ **CUDA**: 12.x, an NVIDIA GPU (required for `flash-attn`)
+- 🔥 **PyTorch**: 2.10
+
+### Installation
+
+1. **Install the specific Transformers version required for this model** (it provides the `hunyuan_vl_mot` backbone that `unified_mot` builds on):
+```bash
+pip install git+https://github.com/huggingface/transformers@9293856c419762ebf98fbe2bd9440f9ce7069f1a
+```
+> **Note:** A stock `transformers` release does **not** yet include `hunyuan_vl_mot`; this pinned commit is required. We will merge the improvements into the Transformers main branch later.
+
+2. **Clone the inference code and install the remaining dependencies:**
+```bash
+git clone https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0.git
+cd Hy-Embodied-RxBrain-1.0
+pip install -r requirements.txt
+```
+
+### Model Download
+
+| Component | Params | Source |
+|---|:---:|---|
+| **Hy-Embodied-RxBrain-1.0** | ~6.2 B | [🤗 tencent/Hy-Embodied-RxBrain-1.0](https://huggingface.co/tencent/Hy-Embodied-RxBrain-1.0) |
+| FLUX VAE (`ae.safetensors`) | 83.8 M | Obtain from the [FLUX](https://github.com/black-forest-labs/flux) distribution |
+
+Download the weights to a **local directory** — the loader reads the checkpoint files directly, so `--ckpt` must be a local path, **not** the Hub repo id:
+
+```bash
+pip install -U "huggingface_hub[cli]"
+hf download tencent/Hy-Embodied-RxBrain-1.0 --local-dir ./Hy-Embodied-RxBrain-1.0
+```
+
+The VQA (understanding) path needs **only** the main weights. Image generation (T2I / world-model rollout / interleaved planning) additionally requires the external **FLUX VAE** `ae.safetensors`.
+
+
+## 🚀 Quick Start with Transformers
+
+Load the Transformers processor together with the `UnifiedMoT` classes shipped in this repo, then run understanding (VQA). Run this from the repo root so the `model` package is importable, and point `MODEL_PATH` at your **local** download (see [Model Download](#model-download)).
+
+```python
+import torch
+from transformers.models.hunyuan_vl_mot import HunYuanVLMoTProcessor
+from model import UnifiedMoTForConditionalGeneration, maybe_init_generation_path
+from vqa_inference import answer
+
+MODEL_PATH = "./Hy-Embodied-RxBrain-1.0"  # local checkpoint directory, not the Hub id
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+dtype = torch.bfloat16
+
+# Load processor & model
+processor = HunYuanVLMoTProcessor.from_pretrained(MODEL_PATH, trust_remote_code=True)
+model = UnifiedMoTForConditionalGeneration.from_pretrained(MODEL_PATH, dtype=dtype)
+maybe_init_generation_path(model, model_load_path=MODEL_PATH)  # wires up the generation path
+model.to(device).eval()
+
+# Ask a question about an image
+text = answer(
+    model, processor,
+    image_paths=["demo_cases/bridgev2_move_toy/input/obs_1.jpg"],
+    question="What objects are on the stovetop, and where is the green toy?",
+    device=device, dtype=dtype, max_new_tokens=256,
+)
+print(text)
+```
+
+> **Note:** RxBrain uses a custom interleaved text/image decoding loop rather than the standard `model.generate` API. The `answer(...)` helper (in `vqa_inference.py`) wraps that loop for the understanding case; image generation and planning have their own entry points below.
+
+The same tasks are also available as ready-to-run scripts:
+
+<details open>
+<summary><b>① Visual Question Answering (VQA)</b> — image(s) + question → answer text</summary>
+
+Pure autoregressive text understanding — **no VAE / flow-matching needed**.
+
+```bash
+python vqa_inference.py \
+    --ckpt ./Hy-Embodied-RxBrain-1.0 \
+    --images demo_cases/bridgev2_move_toy/input/obs_1.jpg \
+    --question "What objects are on the stovetop, and where is the green toy?" \
+    --max_new_tokens 256
+```
+</details>
+
+
+<details open>
+<summary><b>② Text-to-Image (T2I)</b></summary>
+
+```bash
+python text2image_inference.py \
+    --ckpt ./Hy-Embodied-RxBrain-1.0 --vae /path/to/ae.safetensors \
+    --prompt "a watercolor painting of a cat" \
+    --height 256 --width 256 --num_steps 25 --out out.png
+
+# with classifier-free guidance
+python text2image_inference.py \
+    --ckpt ./Hy-Embodied-RxBrain-1.0 --vae /path/to/ae.safetensors \
+    --prompt "a watercolor painting of a cat" \
+    --cfg_scale 5.0 --num_steps 50 --out out.png
+```
+</details>
+
+<details open>
+<summary><b>③ Multi-Frame World-Model Rollout</b> — imagine future frames from an observation</summary>
+
+```bash
+python multiframe_inference.py \
+    --ckpt ./Hy-Embodied-RxBrain-1.0 --vae /path/to/ae.safetensors \
+    --frames /path/to/obs.jpg --task "imagine the next frames" \
+    --num_frames 4 --num_steps 50 --out_dir multiframe_out
+```
+</details>
+
+<details>
+<summary><b>④ Interleaved Embodied Planning</b> — text plan + goal images, step by step</summary>
+
+Runs interleaved planning on a bundled scene. See [`demo_cases/README.md`](https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0/blob/main/demo_cases/README.md) for details.
+
+```bash
+CASE=umi_fold_sock
+python interleave_inference.py \
+    --ckpt ./Hy-Embodied-RxBrain-1.0 --vae /path/to/ae.safetensors \
+    --frames  demo_cases/$CASE/input/*.jpg \
+    --task    "$(cat demo_cases/$CASE/prompt.txt)" \
+    --max_frames 5 --num_steps 50 --out_dir out_$CASE
+```
+</details>
+
+## 📊 Evaluation
+
+RxBrain is evaluated on embodied understanding, spatial reasoning, and imagination/generation benchmarks. For detailed metrics and methodology, please refer to our [technical report](https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0/blob/main/assets/RxBrain_v0.pdf).
+

chat_template.jinja

@@ -0,0 +1,146 @@
+{%- if not add_generation_prompt is defined %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_first_user=true, is_last_user=false) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {%- if ns.is_first_sp %}
+            {%- set ns.system_prompt = ns.system_prompt + message['content'] %}
+            {%- set ns.is_first_sp = false %}
+        {%- else %}
+            {% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{{- bos_token }}
+{{- ns.system_prompt }}
+{%- if tools %}
+    {%- if ns.system_prompt != '' %}
+        {{- '\n\n# Tools\n\nYou may call one or more functions to assist with the user query.' }}
+    {%- else %}
+        {{- '# Tools\n\nYou may call one or more functions to assist with the user query.' }}
+    {%- endif %}
+    {{- '\n\nYou are provided with function signatures within <tools></tools> XML tags:' }}
+    {{- '\n<tools>\n' }}
+    {%- for tool in tools %}
+        {%- if loop.index0 > 1 %}
+            {{- '\n' }}
+        {%- endif %}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- '\n</tools>\n\n' }}
+    {{- 'For function call returns, you should first print <tool_calls>' }}
+    {{- 'For each function call, you should return object like:\n' }}
+    {{- '<tool_call>function_name\n```json\nfunction_arguments_in_json_format\n```</tool_call>' }}
+    {{- 'At the end of function call returns, you should print </tool_calls>' }}
+{%- endif %}
+{%- if ns.system_prompt != '' or tools %}
+    {{- '<｜hy_place▁holder▁no▁3｜>' }}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- set last_user_idx = namespace(value=-1) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'user' %}
+        {%- set last_user_idx.value = loop.index0 %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.is_tool = false %}
+        {%- set ns.is_first = false %}
+        {%- set ns.is_last_user = true %}
+        {{- '<｜hy_User｜>'}}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- 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 -%}
+                    <｜hy_place▁holder▁no▁666｜><｜hy_place▁holder▁no▁669｜><｜hy_place▁holder▁no▁672｜><｜hy_place▁holder▁no▁667｜>
+                {%- 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 -%}
+                    <｜hy_place▁holder▁no▁666｜><｜hy_place▁holder▁no▁670｜><｜hy_place▁holder▁no▁672｜><｜hy_place▁holder▁no▁667｜>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if loop.index0 == last_user_idx.value %}
+            {%- if enable_thinking is defined and enable_thinking %}
+                {{- '/think' }}
+            {%- else %}
+                {{- '/no_think' }}
+            {%- endif %}
+        {%- else %}
+            {{- '/no_think' }}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
+        {%- set ns.is_last_user = false %}
+        {%- if ns.is_tool %}
+            {{- '</tool_responses>' }}
+        {%- endif %}
+        {{- '<｜hy_Assistant｜>' }}
+        {%- set ns.is_first = false %}
+        {%- set ns.is_tool = false %}
+        {%- set ns.is_output_first = true %}
+        {%- for tool in message['tool_calls'] %}
+            {%- set arguments = tool['function']['arguments'] %}
+            {%- if arguments is not string %}
+                {%- set arguments = arguments | tojson %}
+            {%- endif %}
+            {%- if not ns.is_first %}
+                {%- if message['content'] is none %}
+                    {{- '<tool_calls><tool_call>' + tool['function']['name'] + '\n```json\n' + arguments + '\n```</tool_call>' }}
+                {%- else %}
+                    {{- message['content'] + '<tool_calls><tool_call>' + tool['function']['name'] + '\n```json\n' + arguments + '\n```</tool_call>' }}
+                {%- endif %}
+            {%- set ns.is_first = true %}
+            {%- else %}
+                {{- '\n<tool_call>' + tool['function']['name'] + '\n```json\n' + arguments + '\n```</tool_call>' }}
+            {%- endif %}
+        {%- endfor %}
+        {{- '</tool_calls>' + eos_token }}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
+        {%- set ns.is_last_user = false %}
+        {{- '<｜hy_Assistant｜>' }}
+        {{- '<think>\n\n</think>\n' }}
+        {{- '<answer>\n' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content_item in message['content'] %}
+                {%- if 'text' in content_item %}
+                    {{- content_item['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</answer>' }}
+        {{- eos_token }}
+    {%- endif %}
+    {%- if message['role'] == 'tool' %}
+        {%- set ns.is_last_user = false %}
+        {%- set ns.is_tool = true %}
+        {%- if ns.is_output_first %}
+            {{- '<｜hy_User｜>' + '<tool_responses><tool_response>' + message['content'] + '</tool_response>' }}
+            {%- set ns.is_output_first = false %}
+        {%- else %}
+            {{- '\n<tool_response>' + message['content'] + '</tool_response>' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.is_tool %}
+    {{- '</tool_responses>' }}
+{%- endif %}
+{%- if add_generation_prompt %}
+    {{- '<｜hy_Assistant｜>' }}
+    {%- if enable_thinking is defined and enable_thinking %}
+        {{- '<think>' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,169 @@
+{
+  "add_classification_head": false,
+  "architectures": [
+    "UnifiedMoTForConditionalGeneration"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_head_dim": 128,
+  "bos_token_id": 120000,
+  "boundary_loss_weight": 0.0,
+  "cla_share_factor": 2,
+  "class_num": 0,
+  "dense_list": [
+    2048,
+    0
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 120020,
+  "flow_latent_placeholder_id": 120690,
+  "flow_loss_weight": 1.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "im_end_id": 5,
+  "im_newline_id": 11,
+  "im_start_id": 4,
+  "image_end_token_id": 120120,
+  "image_start_token_id": 120119,
+  "image_token_id": 120687,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "latent_patch_size": 2,
+  "latent_token_id": 120690,
+  "mask_init_id": 12,
+  "max_latent_size": 32,
+  "max_position_embeddings": 262144,
+  "mlp_bias": false,
+  "model_type": "unified_mot",
+  "norm_type": "rms",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "org_vocab_size": 120818,
+  "pad_id": 120002,
+  "pad_token_id": 120002,
+  "pool_type": "last",
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "alpha": 1000.0,
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 1.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "type": "dynamic"
+  },
+  "rope_theta": 10000.0,
+  "sep_token_id": 120007,
+  "text_config": {
+    "_name_or_path": "",
+    "add_classification_head": false,
+    "architectures": [
+      "UnifiedMoTForConditionalGeneration"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_head_dim": 128,
+    "cla_share_factor": 2,
+    "class_num": 0,
+    "dense_list": [
+      2048,
+      0
+    ],
+    "dtype": "bfloat16",
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "im_end_id": 5,
+    "im_newline_id": 11,
+    "im_start_id": 4,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "mask_init_id": 12,
+    "max_position_embeddings": 262144,
+    "mlp_bias": false,
+    "mlp_g_init_noise_std": 0.0001,
+    "mlp_g_intermediate_size": 12288,
+    "model_type": "unified_mot",
+    "norm_type": "rms",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "org_vocab_size": 120818,
+    "pad_id": 120002,
+    "pool_type": "last",
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "alpha": 1000.0,
+      "beta_fast": 32,
+      "beta_slow": 1,
+      "factor": 1.0,
+      "mscale": 1.0,
+      "mscale_all_dim": 1.0,
+      "type": "dynamic"
+    },
+    "rope_theta": 10000.0,
+    "sep_token_id": 120007,
+    "text_end_id": 7,
+    "text_start_id": 6,
+    "use_cache": true,
+    "use_cla": false,
+    "use_moe": false,
+    "use_qk_norm": true,
+    "use_rotary_pos_emb": true,
+    "use_varlen_flash_attn": true,
+    "vision_full_attention": false,
+    "vocab_size": 120818
+  },
+  "text_end_id": 7,
+  "text_loss_weight": 1.0,
+  "text_start_id": 6,
+  "timestep_shift": 1.0,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "use_cla": false,
+  "use_qk_norm": true,
+  "use_rotary_pos_emb": true,
+  "vae_image_downsample": 16,
+  "vae_z_channels": 16,
+  "video_end_token_id": 120123,
+  "video_start_token_id": 120122,
+  "vision_config": {
+    "anyres_vit_max_image_size": 2048,
+    "attention_dropout": 0.0,
+    "cat_extra_token": 1,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu",
+    "hidden_size": 1152,
+    "img_max_token_num": 4096,
+    "intermediate_size": 4304,
+    "interpolate_mode": "bilinear",
+    "learnable_mlp_pooling_size": 0,
+    "max_image_size": 2048,
+    "max_vit_seq_len": 16384,
+    "min_image_size": 512,
+    "model_type": "hunyuan_vl_mot",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "num_key_value_heads": 16,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "perceive_post_norm": true,
+    "perceive_pre_norm": true,
+    "remove_prenorm": true,
+    "resize_resolution": 2048,
+    "rms_norm_eps": 1e-05,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 1,
+    "temporal_patch_size": 1,
+    "text_hidden_size": 2048,
+    "video_max_image_size": 768,
+    "video_min_image_size": 256,
+    "vision_full_attention": false
+  },
+  "vocab_size": 120818
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 120000,
+  "eos_token_id": [
+    120020
+  ],
+  "pad_token_id": 120002,
+  "transformers_version": "4.57.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8d2cf13e6056494f89fb49ace96057dd9008371def50641c36a7d05e29d936
+size 4999925816

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c490f84bb2054b6d29866eb070a6c5e002adcfeccfa00d7927e88d22d9ba67d7
+size 4974862032

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413a279bb4afdb55892d8ff25a3118f9013dfd82247513eaa389b5e39944bf20
+size 2441807536

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": 524288,
+  "merge_size": 2,
+  "min_pixels": 25088,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "HunYuanVLMoTProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 524288,
+    "shortest_edge": 25088
+  },
+  "temporal_patch_size": 1
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "bos_token": {
+    "content": "<｜hy_begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜hy_place▁holder▁no▁2｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_newline_token": "<｜hy_place▁holder▁no▁671｜>",
+  "image_token": "<｜hy_place▁holder▁no▁669｜>",
+  "pad_token": {
+    "content": "<｜hy_▁pad▁｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "video_token": "<｜hy_place▁holder▁no▁670｜>",
+  "vision_end_token": "<｜hy_place▁holder▁no▁667｜>",
+  "vision_start_token": "<｜hy_place▁holder▁no▁666｜>"
+}

video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2.0,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 16,
+  "merge_size": 2,
+  "min_frames": 8,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "HunYuanVLMoTProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 134217728,
+    "shortest_edge": 100352
+  },
+  "temporal_patch_size": 1,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}