PAN2

Co-authored-by: gxchris95 <gxchris95@users.noreply.huggingface.co>
Co-authored-by: hongyixu2008 <hongyixu2008@users.noreply.huggingface.co>
Co-authored-by: wuqing157 <wuqing157@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,51 @@
+*.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/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/report/architecture.png filter=lfs diff=lfs merge=lfs -text
+assets/report/captioning_pipeline.png filter=lfs diff=lfs merge=lfs -text
+assets/report/data_taxonomy.png filter=lfs diff=lfs merge=lfs -text
+assets/report/tier1_capabilities.png filter=lfs diff=lfs merge=lfs -text
+assets/report/tier2_tsr.png filter=lfs diff=lfs merge=lfs -text
+assets/report/simulative_reasoning_puzzle.jpg filter=lfs diff=lfs merge=lfs -text
+assets/report/simulative_reasoning_surfing.jpg filter=lfs diff=lfs merge=lfs -text
+assets/report/results_benchmarks_dark.png filter=lfs diff=lfs merge=lfs -text
+assets/report/results_benchmarks_light.png filter=lfs diff=lfs merge=lfs -text
+assets/report/results_capabilities_dark.png filter=lfs diff=lfs merge=lfs -text
+assets/report/results_capabilities_light.png filter=lfs diff=lfs merge=lfs -text
+assets/report/results_human_dark.png filter=lfs diff=lfs merge=lfs -text
+assets/report/results_human_light.png filter=lfs diff=lfs merge=lfs -text
+assets/video.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/video_preview.gif filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 2026 Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
+
+   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.

NOTICE

@@ -0,0 +1,10 @@
+PAN 2
+Copyright 2026 Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
+Developed by the Institute of Foundation Models (IFM) at MBZUAI
+
+This product includes or is used with the following third-party components, each licensed under the terms set out in THIRD_PARTY_LICENSES:
+- Wan 2.2, Copyright 2024-2025 The Alibaba Wan Team Authors, licensed under the Apache License, Version 2.0
+- Qwen (Qwen3.5-9B), Copyright 2026 Alibaba Cloud, licensed under the Apache License, Version 2.0
+- Diffusers, Copyright 2025 Stability AI, Katherine Crowson, HuggingFace Inc. and The HuggingFace Team, licensed under the Apache License, Version 2.0
+
+The names of the third-party components and their owners are used solely to identify the origin of those components and do not imply any endorsement of PAN 2.

README.md

@@ -0,0 +1,237 @@
+---
+pipeline_tag: image-text-to-video
+license: apache-2.0
+license_link: LICENSE
+library_name: pan
+tags:
+  - world-model
+  - world-simulation
+  - text-to-video
+  - image-to-video
+  - image-text-to-video
+  - diffusion-transformer
+language:
+  - en
+---
+
+<div align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/IFM/PAN2-TEST/resolve/main/assets/pan2-logo-dark.png">
+    <img alt="PAN 2" src="assets/pan2-logo-light.png" width="420">
+  </picture>
+</div>
+
+<p align="center">
+  <a href="https://github.com/ifm-ai/PAN2" target="_blank"><img src="https://img.shields.io/badge/GitHub-181717?logo=github&logoColor=white" alt="GitHub"></a>
+  <a href="https://huggingface.co/IFM/PAN2" target="_blank"><img src="https://img.shields.io/badge/Hugging%20Face-FFD21E?logo=huggingface&logoColor=black" alt="Hugging Face"></a>
+  <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/pan2" target="_blank"><img src="https://img.shields.io/badge/Diffusers-FF9D00?logo=huggingface&logoColor=white" alt="Diffusers"></a>
+  <a href="https://recipes.vllm.ai/IFM/PAN2" target="_blank"><img src="https://img.shields.io/badge/vLLM-30A2FF?logoColor=white" alt="vLLM"></a>
+  <a href="https://github.com/ifm-ai/PAN2/blob/main/README.md" target="_blank"><img src="https://img.shields.io/badge/Docs-4f8cff?logo=readthedocs&logoColor=white" alt="Docs"></a>
+  <a href="https://github.com/ifm-ai/PAN2/blob/main/LICENSE" target="_blank"><img src="https://img.shields.io/badge/LICENSE-Apache%202.0-4CAF50?logo=apache&logoColor=white" alt="LICENSE"></a>
+</p>
+
+# PAN 2
+
+Developed by the Institute of Foundation Models (IFM) at MBZUAI.
+
+<video src="https://huggingface.co/IFM/PAN2-TEST/resolve/main/assets/video.mp4" width="100%" autoplay loop muted playsinline></video>
+
+## Overview
+
+PAN 2 is a general-purpose world model: it simulates how the world will change in response to actions. Given a current observation (an optional image plus text) and actions described in text, it simulates the outcome as a video of up to 20 seconds. This supports *simulative reasoning*: an agent can imagine the outcomes of its candidate actions before choosing among them, by simulating each plan with PAN 2 and acting on the one whose simulated outcome is best.
+
+PAN 2 follows the Generative Latent Prediction (GLP) architecture formalized in [Critique of World Models](https://arxiv.org/abs/2507.05169) and couples **conceptual reasoning** by a large language model with **perceptual reasoning** by a latent diffusion model. The language model, the **conceptual reasoning backbone**, reasons over the observation and the requested actions and writes the next world state as a structured, time-grounded description of events, timed actions bound to actors, and camera motion. The frozen text encoder maps the structured description to the conditioning features used by the diffusion model. The 29B-parameter MMDiT, the **perceptual reasoning backbone**, trained from scratch on hundreds of millions of videos annotated in the same format, predicts the perceptual detail that the description leaves open: the video latents that realize the state, conditioned on it and on the VAE latent of the starting image. The Wan 2.2 VAE decoder renders the predicted latents as the next observation, so every prediction can be seen and checked against real footage.
+
+## Checkpoints
+
+PAN 2's latent diffusion model is released as a single checkpoint that serves both tasks. The frozen text encoder (Qwen3.5-9B) and VAE (Wan 2.2) are downloaded from their own repositories.
+
+|Checkpoint|Supported Tasks|Input Conditions|Output|Precision|
+|---|---|---|---|---|
+|PAN 2 diffusion backbone (`IFM/PAN2`)|Text-to-video (`t2v`), Image-to-video (`i2v`)|Structured world-state caption; optional first frame|Video via the VAE decoder, 704x1248 at 24 fps, up to 20 s|BF16|
+
+## Usage
+
+PAN 2 is also supported in [Diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/pan2) and [vLLM](https://recipes.vllm.ai/IFM/PAN2); the instructions below use this repository's `generate.py`.
+
+### Local Deployment of the PAN 2 Simulator
+
+The released perceptual backbone weights are in the diffusers layout (`PAN2Transformer3DModel`). Download them and convert them once for this repository's `generate.py`:
+
+```bash
+hf download IFM/PAN2 --include "transformer/*" --local-dir /path/to/PAN2
+python scripts/convert_checkpoint.py to-native \
+    --input /path/to/PAN2/transformer --output <DIR>/transformer
+```
+
+Then pass `<DIR>/transformer` as `CKPT_PATH` below.
+
+**Environment** (see [docs/environment.md](https://github.com/ifm-ai/PAN2/blob/main/docs/environment.md)):
+
+```bash
+conda create -n pan python=3.14 -y && conda activate pan
+pip install torch==2.12.1 torchvision==0.27.1 --index-url https://download.pytorch.org/whl/cu132
+pip install --pre "flash-attn-4[cu13]==4.0.0b29" --no-build-isolation
+pip install "quack-kernels[cu13]==0.6.4"
+pip install -r requirements.txt
+```
+
+**Frozen components** (text encoder and VAE, fetched from the Hugging Face cache at `HF_HOME`):
+
+```bash
+export HF_HOME=YOUR_HF_PATH
+hf download Qwen/Qwen3.5-9B
+hf download Wan-AI/Wan2.2-TI2V-5B-Diffusers
+```
+
+**Checkpoint.** `CKPT_PATH` is a training `checkpoint-N/transformer` directory (DCP), a `model_state.pt`, or a directory of `*.safetensors`. The architecture is read from `config/sft_29B_720p.yaml`; no model root is needed.
+
+**Generate** (single node, one `generate.py` worker per GPU; each worker holds the full 29B diffusion model and takes every N-th prompt):
+
+```bash
+bash inference/inference.sh <CKPT_PATH> <OUTPUT_DIR> [PROMPTS_JSON]   # or sbatch, same arguments
+```
+
+`PROMPTS_JSON` defaults to `inference/prompts/examples.json` (one `t2v` and one `i2v` record with structured negatives and a reference image). Any entry with an `image_path` (or `type: i2v`) runs as image-to-video. Videos land in `<OUTPUT_DIR>/{t2v,i2v}/` next to a `*_config.json`; a rerun into the same directory skips finished clips.
+
+Default sampler:
+
+| Control | Value |
+|---|---|
+| Steps / flow shift | 50 / 9 |
+| Classifier-free guidance | 2.5 on every step |
+| Resolution / frame rate | 704 x 1248 at 24 fps |
+| Frames | 241 (about 10 s) for entries without a duration; up to 481 (20 s) |
+| Seed | 123 |
+| Precision | bf16 transformer |
+| I2V | temporal latent 0 uses the positive prediction without guidance |
+
+Override any default through environment variables (`NUM_STEPS`, `FLOW_SHIFT`, `GUIDANCE_SCALE`, `VIDEO_LENGTH`, `SEED`, `NUM_GPUS`, ...) or pass extra `generate.py` flags in `EXTRA_ARGS` (CFG windows, skip-layer guidance, timestep schedules). See [docs/inference.md](https://github.com/ifm-ai/PAN2/blob/main/docs/inference.md).
+
+### Full PAN 2 Workflow
+
+The full workflow runs the conceptual reasoner on a free-text prompt, then the locally deployed perceptual pipeline on its structured output.
+
+<table>
+  <thead>
+    <tr><th>stage</th><th>request</th><th>result</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>Conceptual reasoner</td><td><a href="https://github.com/ifm-ai/PAN2/blob/main/inference/pan-prompt-rewriter/SKILL.md">PAN 2 Conceptual Reasoner (Prompt Rewriter) skill</a>, or <code>python inference/prompts_rewritter.py</code> with a local instruction-tuned model</td><td>The prompt JSON with a structured <code>refined_prompts</code> world-state caption added to each record</td></tr>
+    <tr><td>Perceptual pipeline</td><td><code>bash inference/inference.sh &lt;CKPT_PATH&gt; &lt;OUTPUT_DIR&gt; &lt;REWRITTEN_JSON&gt;</code></td><td><code>&lt;OUTPUT_DIR&gt;/{t2v,i2v}/*.mp4</code>, each next to a <code>*_config.json</code></td></tr>
+  </tbody>
+</table>
+
+See [docs/inference.md](https://github.com/ifm-ai/PAN2/blob/main/docs/inference.md#5-prompt-rewriting) for the prompt JSON format.
+
+### Prompting Guidance
+
+The PAN 2 perceptual backbone is conditioned on structured world-state captions, so prompts work best in that format. Free-text prompts should be rewritten by a conceptual reasoner before generation.
+
+- [PAN 2 Conceptual Reasoner skill](https://github.com/ifm-ai/PAN2/blob/main/inference/pan-prompt-rewriter/SKILL.md): a Codex / Claude Code agent skill carrying the caption policy ([system_prompt.md](https://github.com/ifm-ai/PAN2/blob/main/inference/pan-prompt-rewriter/system_prompt.md)), the fixed negative prompt, and a validator for the text-encoder token budget (soft limit 1,480, hard capacity 1,536 tokens per caption).
+- `inference/prompts_rewritter.py`: offline rewriting with a local instruction-tuned model.
+- [docs/inference.md](https://github.com/ifm-ai/PAN2/blob/main/docs/inference.md#5-prompt-rewriting): prompt JSON format and rewriting.
+
+Reasoners evaluated in the report, in order of full-plan completion: Claude Opus 5.5, GPT-6 Astra (medium effort), Kimi K3, Qwen 3.8 Flash. Any instruction-following LLM can be used.
+
+## Headline Results
+
+The technical report uses Kimi K3 for all studies unless stated otherwise.
+
+### Simulation Capabilities and Multi-step Plans
+
+Six capabilities: 300 single-action test cases (201 I2V, 99 T2V), accuracy (%). Multi-step plans: 100 egocentric everyday tasks posed as I2V and T2V (200 prompts, 456 steps), step completion (%) and full-plan completion (share of simulations with every step completed, %). Mean ± SD over 3 seeds; † single seed for closed-source models.
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/IFM/PAN2-TEST/resolve/main/assets/report/results_capabilities_dark.png">
+    <img alt="Capability and multi-step plan results, PAN 2 highlighted" src="assets/report/results_capabilities_light.png" width="100%">
+  </picture>
+</p>
+
+### Public Benchmarks
+
+Physics-IQ Verified (I2V) is normalized so that the variance between two real takes is 100 (public leaderboard setting: leaderboard entries, PAN 2 with Claude Opus 5.5 as the conceptual reasoner, mean ± SD over seeds 123–126; system default setting: each model's own default pipeline run by us). PhyGround is on a 5-point scale judged by Qwen3.8-27B. RBench is the unweighted mean over five task and four embodiment categories, multiplied by 100. † closed models generated once through the fal API.
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/IFM/PAN2-TEST/resolve/main/assets/report/results_benchmarks_dark.png">
+    <img alt="Public benchmark results, PAN 2 highlighted" src="assets/report/results_benchmarks_light.png" width="100%">
+  </picture>
+</p>
+
+### Human Evaluation
+
+Blind pairwise preference on 140 prompts (90 T2V, 50 I2V) judged on action adherence, physics and world consistency by 13 reviewers over 1,400 comparisons. Elo from a Bradley–Terry fit centered at 1500, with 95% confidence intervals.
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/IFM/PAN2-TEST/resolve/main/assets/report/results_human_dark.png">
+    <img alt="Human evaluation: Elo with 95% confidence intervals and win rates, PAN 2 highlighted" src="assets/report/results_human_light.png" width="100%">
+  </picture>
+</p>
+
+## Safety Guardrails
+
+We strongly recommend running PAN 2 behind [`pan2-guardrail`](https://github.com/ifm-ai/pan2-guardrail), which screens the request with [Qwen3Guard-Gen-4B](https://huggingface.co/Qwen/Qwen3Guard-Gen-4B) before generation and the generated video with the [Q16](https://huggingface.co/IFM/PAN2-guardrail-Q16) frame classifier after it. Use both guards. The guardrail is distributed separately; see its repository for installation and usage.
+
+In internal evaluations with Kimi K3 as the conceptual reasoner, the guardrail reduced the share of harmful T2V requests that yield an unsafe video from 33.9% to 1.5%, and no unsafe I2V outputs were observed. It also stopped 11.5% of benign T2V requests and 3.3% of benign I2V requests. See [`pan2-guardrail`](https://github.com/ifm-ai/pan2-guardrail) for more details.
+
+The guardrails reduce, but do not eliminate, the risk of harmful outputs, and users remain responsible for reviewing generated content and for their use of the model.
+
+## Intended Uses
+
+PAN 2 is intended for research and development in world modeling and simulative reasoning, including simulating the outcomes of actions for agents and robotics, studying physical and causal reasoning in video, and generating video for evaluation, education, and creative work.
+
+## Out-of-Scope Uses
+
+PAN 2 should not be used to:
+
+- create content that impersonates or depicts real, identifiable people without their consent, including deepfakes;
+- create or spread misinformation, including content presented as real footage of events that did not occur;
+- generate sexual content involving minors, non-consensual intimate content, or content that promotes violence, harassment or discrimination;
+- infringe the intellectual property, privacy or other rights of others; or
+- make decisions about people or safety-critical decisions (e.g. in medical, legal or physical control systems) without independent human review and validation.
+
+PAN 2's simulations are predictions, not records of real events, and should not be relied on as evidence of what happened or will happen.
+
+## Training
+
+The shipped configs `config/pretrain_29B_720p.yaml` and `config/sft_29B_720p.yaml` define the diffusion model architecture; point their `data` paths at your own latents, see [docs/training.md](https://github.com/ifm-ai/PAN2/blob/main/docs/training.md).
+
+## Limitations
+
+- **Long plans fail often.** About two in three simulated plans contain at least one step that is not carried out. The quantitative study covers open-loop plans designed to succeed; how faithfully PAN 2 simulates plans that should fail is not yet measured.
+- **Prompt sensitivity.** Like related models, PAN 2 is sensitive to the wording of the prompt describing the observation and action; the examples beyond the training data and the agent case studies relied on hand-refined prompts.
+- **Long-horizon consistency.** Each clip is simulated from at most one starting frame plus text, so appearance drifts across clips in long interactions; a perceptual memory maintained alongside the text-based state would be needed to address this.
+- **Text actions are coarse.** Text suits actions that can be stated as concepts, such as opening a drawer, but specifies dexterous ones, such as where each finger meets an object, only coarsely.
+- **Shortcuts.** PAN 2 may let a simulation progress while violating physical constraints (e.g. pasta appearing in the colander before it is drained), which matters for uses that depend on the intermediate states.
+- **Realistic synthetic video.** PAN 2 can generate realistic video that may be mistaken for real footage. Users should disclose that content is AI-generated where it could mislead.
+- **Bias and representation.** PAN 2 was trained on large-scale video data and may reflect biases or gaps in that data, including in how people, places, and activities are depicted.
+
+## Responsible Use
+
+PAN 2 is released under the Apache License, Version 2.0. We ask everyone who uses PAN 2 to do so responsibly, in line with applicable laws and the out-of-scope uses described above, to run it with the recommended guardrails, and to be transparent when sharing content generated with it. Concerns about misuse, security, or intellectual property can be reported to [pan@ifm.ai](mailto:pan@ifm.ai).
+
+## License
+
+- PAN 2 is developed by the Institute of Foundation Models (IFM) at MBZUAI. Its own code and weights are released under the [Apache License, Version 2.0](https://huggingface.co/IFM/PAN2-TEST/blob/main/LICENSE).
+- Third-party components (Wan 2.2, Qwen3.5-9B and Diffusers) are used under their own licenses; see [NOTICE](https://huggingface.co/IFM/PAN2-TEST/blob/main/NOTICE) and [THIRD_PARTY_LICENSES](https://huggingface.co/IFM/PAN2-TEST/blob/main/THIRD_PARTY_LICENSES). The Wan 2.2 and Qwen3.5-9B weights are used as released by their authors and have not been modified or fine-tuned by MBZUAI. Third-party code adapted in this repository keeps its original copyright and license header, with a notice describing MBZUAI's changes.
+
+## Citation
+
+```bibtex
+@misc{pan2_2026,
+  title        = {PAN 2},
+  author       = {{PAN Team}},
+  organization = {Institute of Foundation Models, Mohamed bin Zayed University of Artificial Intelligence},
+  year         = {2026},
+  month        = oct,
+  howpublished = {\url{https://huggingface.co/IFM/PAN2}},
+  url          = {https://huggingface.co/IFM/PAN2}
+}
+```
+
+## Contact Us
+
+For questions and bugs, open an issue on [GitHub](https://github.com/ifm-ai/PAN2/issues). To report misuse, security or IP concerns, email [pan@ifm.ai](mailto:pan@ifm.ai).

THIRD_PARTY_LICENSES

@@ -0,0 +1,635 @@
+PAN 2
+Copyright 2026 Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
+Developed by the Institute of Foundation Models (IFM) at MBZUAI
+
+This product includes or is used with the following third-party components. The full license text of each component is reproduced below:
+- Wan 2.2, Copyright 2024-2025 The Alibaba Wan Team Authors, licensed under the Apache License, Version 2.0
+- Qwen (Qwen3.5-9B), Copyright 2026 Alibaba Cloud, licensed under the Apache License, Version 2.0
+- Diffusers, Copyright 2025 Stability AI, Katherine Crowson, HuggingFace Inc. and The HuggingFace Team, licensed under the Apache License, Version 2.0
+
+================================================================================
+Wan 2.2
+Copyright 2024-2025 The Alibaba Wan Team Authors
+License: Apache License 2.0
+Source: https://github.com/Wan-Video/Wan2.2
+================================================================================
+
+                                 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.
+
+================================================================================
+Qwen (Qwen3.5-9B)
+Copyright 2026 Alibaba Cloud
+License: Apache License 2.0
+Source: https://huggingface.co/Qwen/Qwen3.5-9B
+================================================================================
+
+                                 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 2026 Alibaba Cloud
+
+   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.
+
+================================================================================
+Diffusers
+Copyright 2025 Stability AI, Katherine Crowson, HuggingFace Inc. and The HuggingFace Team
+License: Apache License 2.0
+Source: https://github.com/huggingface/diffusers
+================================================================================
+
+                                 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.

assets/video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538786a8efcf4a71bff8f0cf405b6daae1bba7d16b8753bf922d073c2c0d9cab
+size 79741832

modular_model_index.json

@@ -0,0 +1,75 @@
+{
+  "_class_name": "PAN2ModularPipeline",
+  "_diffusers_version": "0.41.0.dev0",
+  "_blocks_class_name": "PAN2Blocks",
+  "transformer": [
+    "diffusers",
+    "PAN2Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "PAN2Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "IFM/PAN2",
+      "subfolder": "transformer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLWan",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLWan"
+      ],
+      "pretrained_model_name_or_path": "IFM/PAN2",
+      "subfolder": "vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "FlowMatchEulerDiscreteScheduler"
+      ],
+      "pretrained_model_name_or_path": "IFM/PAN2",
+      "subfolder": "scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3_5TextModel",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3_5TextModel"
+      ],
+      "pretrained_model_name_or_path": "IFM/PAN2",
+      "subfolder": "text_encoder",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen2Tokenizer"
+      ],
+      "pretrained_model_name_or_path": "IFM/PAN2",
+      "subfolder": "tokenizer",
+      "variant": null,
+      "revision": null
+    }
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.41.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 9.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,83 @@
+{
+  "architectures": [
+    "Qwen3_5TextModel"
+  ],
+  "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": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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_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": 32,
+  "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": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "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,
+  "transformers_version": "5.19.0",
+  "use_cache": true,
+  "vocab_size": 248320
+}

text_encoder/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f209d5299e87bbcc7de2c12e3a4b49cb56a06cd0bed6ae9a60fd5432dd6c67
+size 4973901040

text_encoder/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:365021e5a60c859a936e23b879695f4c7bce2cc008541afe173efdbde0500bab
+size 4988361936

text_encoder/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a8bd6ee80a0f126925c278c4e01ef2ffa8410490a369c3d619e6d350757d0e
+size 4954199896

text_encoder/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d65389f300e39d4f56840c480ad791d9c6c49d3fc044962d83785b388b7192
+size 956953032

text_encoder/model.safetensors.index.json

@@ -0,0 +1,434 @@
+{
+  "metadata": {
+    "total_parameters": 7936684544,
+    "total_size": 15873369088
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.18.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.29.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.6.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

tokenizer/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 false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5cd9732badce41de57e6efce8302930ded1c1188c5f81feb2bd6c24c4a1941f
+size 19989339

tokenizer/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "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": "<|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|>"
+  ],
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "merges_file": null,
+  "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+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen3_5Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

transformer/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "PAN2Transformer3DModel",
+  "_diffusers_version": "0.41.0.dev0",
+  "attention_head_dim": 128,
+  "context_mlp_ratio": 4.0,
+  "in_channels": 97,
+  "mlp_ratio": 8.0,
+  "num_attention_heads": 32,
+  "num_layers": 44,
+  "num_refiner_layers": 4,
+  "out_channels": 48,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "refiner_mlp_ratio": 4.0,
+  "rope_axes_dim": [
+    16,
+    56,
+    56
+  ],
+  "rope_temporal_scale": 0.6666666666666666,
+  "rope_theta": 256.0,
+  "text_embed_dim": 4096
+}

transformer/diffusion_pytorch_model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8738b02827609e260992ff4d61b28f4794b849e9a7e728cf7052a4d4edf03da8
+size 4940734352

transformer/diffusion_pytorch_model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cdf7d2461bba6a56d81b38a536d7696aae796956ab73b275b4cb9762e779a07
+size 4698904784

transformer/diffusion_pytorch_model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0b058d1936791187662d1f1160d942529b35ca4c26d2666d0f7e7d9e670eaf
+size 4967333320

transformer/diffusion_pytorch_model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b875b3aff19f83153ecb0901cebbcf73003b0ee0477d769e6b3a59557f4d13
+size 4833082928

transformer/diffusion_pytorch_model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ceebe0ef17fcf2e0ef2e012b9e8994df571cea23d26d3c26d8301f0b7833412
+size 4967348760

transformer/diffusion_pytorch_model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c047d21312f1dc986daddff49f3fb8e112738e22f911880381243a9a8a70d9e
+size 4967333424

transformer/diffusion_pytorch_model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9684e8fde9c4370c5705d1777593281b9f77fadd0ba6403ba2289cf1377ec581
+size 4833082976

transformer/diffusion_pytorch_model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc09ad83b933de66fd73a67abf59eb8c0b6c009c98637d07cce9d6098405e76
+size 4967348760

transformer/diffusion_pytorch_model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ade00b40e0b0c5de581281bd7e1bd1daf642d57058a4f008b3aca646a07cf2c
+size 4967333424

transformer/diffusion_pytorch_model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9142716e0ae6b60d6c6f68807ca2345df89d89db102cf406d7d607732d39c0d4
+size 4833082976

transformer/diffusion_pytorch_model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc81fdbaf9dc91421a9209d34e2bdd9779ac94793a244dde6197b45f1542fb79
+size 4967348760

transformer/diffusion_pytorch_model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7fa833fbb80f15c306fed80e7fff23dc2cd1751a444dfb00b61f2ad1b46772
+size 4967333424

transformer/diffusion_pytorch_model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53eb3cede5a5398f5d08c6e48401c48cf126d67792e3c0e8c48f5ab72d8b4b6a
+size 4833082976

transformer/diffusion_pytorch_model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43305eabf267ec14006583bca996888ccd9a05ad0d28ec1b144235451c2645a
+size 3626297928

vae/config.json

@@ -0,0 +1,129 @@
+{
+  "_class_name": "AutoencoderKLWan",
+  "_diffusers_version": "0.41.0.dev0",
+  "_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
+  "attn_scales": [],
+  "base_dim": 160,
+  "clip_output": false,
+  "decoder_base_dim": 256,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "in_channels": 12,
+  "is_residual": true,
+  "latents_mean": [
+    -0.2289,
+    -0.0052,
+    -0.1323,
+    -0.2339,
+    -0.2799,
+    0.0174,
+    0.1838,
+    0.1557,
+    -0.1382,
+    0.0542,
+    0.2813,
+    0.0891,
+    0.157,
+    -0.0098,
+    0.0375,
+    -0.1825,
+    -0.2246,
+    -0.1207,
+    -0.0698,
+    0.5109,
+    0.2665,
+    -0.2108,
+    -0.2158,
+    0.2502,
+    -0.2055,
+    -0.0322,
+    0.1109,
+    0.1567,
+    -0.0729,
+    0.0899,
+    -0.2799,
+    -0.123,
+    -0.0313,
+    -0.1649,
+    0.0117,
+    0.0723,
+    -0.2839,
+    -0.2083,
+    -0.052,
+    0.3748,
+    0.0152,
+    0.1957,
+    0.1433,
+    -0.2944,
+    0.3573,
+    -0.0548,
+    -0.1681,
+    -0.0667
+  ],
+  "latents_std": [
+    0.4765,
+    1.0364,
+    0.4514,
+    1.1677,
+    0.5313,
+    0.499,
+    0.4818,
+    0.5013,
+    0.8158,
+    1.0344,
+    0.5894,
+    1.0901,
+    0.6885,
+    0.6165,
+    0.8454,
+    0.4978,
+    0.5759,
+    0.3523,
+    0.7135,
+    0.6804,
+    0.5833,
+    1.4146,
+    0.8986,
+    0.5659,
+    0.7069,
+    0.5338,
+    0.4889,
+    0.4917,
+    0.4069,
+    0.4999,
+    0.6866,
+    0.4093,
+    0.5709,
+    0.6065,
+    0.6415,
+    0.4944,
+    0.5726,
+    1.2042,
+    0.5458,
+    1.6887,
+    0.3971,
+    1.06,
+    0.3943,
+    0.5537,
+    0.5444,
+    0.4089,
+    0.7468,
+    0.7744
+  ],
+  "num_res_blocks": 2,
+  "out_channels": 12,
+  "patch_size": 2,
+  "scale_factor_spatial": 16,
+  "scale_factor_temporal": 4,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 48
+}