Add Open-H3-Regenerate-2K weights

LICENSE-Qwen.txt

@@ -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 [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.

NOTICE

@@ -0,0 +1 @@
+MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved.

README.md

@@ -0,0 +1,83 @@
+---
+license: other
+license_name: minimax-h3-community
+license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/6818f6c32d12b210915e44ad56a4228c2608f160/LICENSE
+base_model: MiniMaxAI/MiniMax-H3
+pipeline_tag: video-to-video
+tags:
+- minimax-h3
+- lora
+- video-refinement
+- sol-engine
+---
+
+# Open-H3-Regenerate-2K
+
+An open replacement for the closed H3-Regenerate-2K API: a three-step MiniMax-H3 refinement pass that regenerates a
+768P H3 draft (1344×768, 121 frames) at **2560×1440**.
+
+[Project page](https://nvlabs.github.io/Sana/Open-H3-Regenerate-2K/) ·
+[Code](https://github.com/NVlabs/Sana/tree/sol-engine/models/Open-H3-Regenerate-2K)
+
+## Speed on one B200
+
+One 5 s clip, 768P latent → 2560×1440 video: latent upscale + 3-step refine + VAE decode, warm, median of 3 runs:
+
+| Forward | VAE decoder | Total | Speedup |
+|---|---|---:|---:|
+| `standard_fwd` (dense attention, BF16) | released H3 VAE | 87.26 s | 1.00× |
+| `sol_engine_fwd` (Sol-Attn, MXFP8, CUDA graphs) | released H3 VAE | 37.39 s | 2.33× |
+| `sol_engine_fwd` (Sol-Attn, MXFP8, CUDA graphs) | fast H3 VAE decoder | 22.45 s | 3.89× |
+
+The fast H3 VAE decoder is the non-causal 24-layer decoder of
+[StreamRender-H3](https://nvlabs.github.io/Sana/Sol-Engine/StreamRender-H3/), distilled from the released H3 VAE;
+it decodes the 2560×1440 clip in 1.6 s instead of 15 s. Latent upscale + refine alone go from 73.11 s to 20.46 s (3.57×).
+
+Per-module numbers are in the code README.
+
+## Files
+
+| Path | Content |
+|---|---|
+| `lora/open_h3_regenerate_2k_lora.safetensors` | One merged LoRA (FP32, rank 576 on 312 linears, scale 1) |
+| `lora/sharp_curve_branches.safetensors` | The 50 LMS Sharp curve AdaLN branches (FP32) |
+| `lora/lora_config.json`, `lora/module_ranks.json` | Sources, hashes, per-module ranks |
+| `lora/MERGE_VERIFY.json` | Merge check against the three separate adapters |
+| `latent_upsampler/` | Author 3D-conv latent upscaler, BF16 |
+| `vae_fast/fast_h3_vae_noncausal_24l.safetensors` | Fast H3 VAE decoder from StreamRender-H3 (non-causal, 24 layers, 1.62B parameters) |
+| `base_model/` | MiniMax-H3 Diffusers components (transformer, VAE, audio VAE, text encoder, tokenizer, processor, schedulers), unmodified copy of revision `6818f6c` |
+
+`base_model/` mirrors [MiniMaxAI/MiniMax-H3 @ 6818f6c](https://huggingface.co/MiniMaxAI/MiniMax-H3/tree/6818f6c32d12b210915e44ad56a4228c2608f160)
+without changes (the native `FL2VA/`, `Ref2VA/` and `transformer_ref/` folders are left out). `download.py` in the code
+folder fetches everything here plus the optional HyperFlow 8-step adapter and Sharp's 1025×8 `adaln_t_table`
+(a base-derived tensor, read by byte range from `Comfy-Org/MiniMax-H3`).
+
+## What the LoRA contains
+
+The reference recipe applies three adapters to the MiniMax-H3 transformer:
+
+| Adapter | Rank / alpha |
+|---|---|
+| Open-H3 refiner, step 5000 EMA | 384 / 384 |
+| LightX2V FL2VA Turbo v1.2 | 128 / 8 |
+| LMS Sharp v1.0 | 64 |
+
+They are merged by concatenating the factors along the rank axis with the strengths (and Turbo's alpha/rank) folded
+into `B`, so `B @ A` equals the sum of the three scaled deltas exactly. Over all 312 linears the merged delta
+matches the separate adapters to a relative error of 2.2e-8 (`MERGE_VERIFY.json`). Sharp's curve branches take an
+8-D timestep curve instead of the layer input, so they are kept as separate modules.
+
+Sampling: three Euler steps on sigmas `[0.909375, 0.857143, 0.666667, 0]`, CFG 1, initial state
+`(1 - 0.909375) * upscaled + 0.909375 * noise`, model time `1 - sigma`.
+
+## License
+
+The refiner LoRA, the fast H3 VAE decoder and `base_model/` follow the
+[MiniMax H3 Community License](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/6818f6c32d12b210915e44ad56a4228c2608f160/LICENSE),
+including its territory, use and redistribution terms. The components we did not train follow their own licenses:
+the [latent upscaler](https://github.com/LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler), and the
+[LightX2V FL2VA Turbo](https://huggingface.co/lightx2v/Minimax-h3-Turbo/tree/3ec17a324ced54151364f24f8b5fb6bf7e26414f) and
+[LMS Sharp](https://huggingface.co/Alissonerdx/Minimax-H3-ComfyUI/blob/main/loras/minimax_h3_lms_v1.0_r64.safetensors)
+LoRAs merged into our LoRA. This bundle is not
+covered by a single blanket license. The runtime code's license does not replace
+model licenses.

base_model/LICENSE

@@ -0,0 +1,84 @@
+MiniMax H3 COMMUNITY LICENSE AGREEMENT
+MiniMax H3 release date/License date: August 2, 2026.
+The scope of this License Agreement (this “Agreement”) is expressly limited to the “Applicable Territory” as defined below.
+By clicking to accept, or by using, reproducing, modifying, distributing, running, or displaying any portion or element of the MiniMax H3 Works (including through any Hosted Services) in any manner, you acknowledge and accept the terms of this Agreement, and this Agreement shall take immediate effect upon the occurrence of such act.
+I.  Definitions
+1. “Acceptable Use Policy” means the policy published by MiniMax in Exhibit A.
+2. “Agreement” means the terms and conditions set forth herein that govern the use, reproduction, distribution, modification, running, and display of the MiniMax H3 Works or any portion or element thereof.
+3. “Applicable Territory” means worldwide, excluding the Excluded Territories.
+4. “Documentation” means the specifications, manuals, and documentation concerning MiniMax H3 that are publicly released by MiniMax.
+5. “Excluded Territories” means the European Union, the United Kingdom, the Republic of Korea and the United States of America.  
+6. “MiniMax H3” means the video generation model, together with its software and algorithms, including trained model weights, parameters (including optimizer states), machine-learning model code, inference-supporting code, and other elements thereof made publicly available by Us, as released at https://huggingface.co/MiniMaxAI/MiniMax-H3.
+7. “MiniMax H3 Works” means (i) the Materials, (ii) the Model Derivatives, and (iii) all derivatives thereof.
+8. “Hosted Services” means hosted services provided via application programming interfaces (APIs), web access, or any other electronic or remote means.
+9. “Licensee,” “you,” or “your” means the natural or legal person exercising rights and/or using the MiniMax H3 Works for any purpose in any field of use under this Agreement.
+10. “Materials” means, collectively, MiniMax H3 and the Documentation (and any portion thereof), in each case as made available by MiniMax under this Agreement and proprietary to MiniMax.
+11. “Model Derivatives” means all of the following: (i) any modification of MiniMax H3 or any Model Derivative thereof; (ii) any work based on MiniMax H3 or any Model Derivative thereof; or (iii) any other machine learning model created by transferring the patterns of the weights, parameters, operational patterns, or Outputs of MiniMax H3 or any Model Derivative thereof to another model, such that the latter model exhibits behavior similar to MiniMax H3 or its Model Derivatives, including by distillation methods, methods using intermediate data representations, or methods based on training using synthetic-data Outputs generated by MiniMax H3 or its Model Derivatives. For the avoidance of doubt, Outputs are not deemed Model Derivatives.
+12. “Output” means any result of operating or otherwise using MiniMax H3 or any Model Derivatives (including through Hosted Services).
+13. “Third Party” means any natural or legal person that is not under common control with us or with you.
+14. “Including” means “including but not limited to.”
+15. “We,” “Us”  or  “MiniMax” means Nanonoble Pte. Ltd..
+II.  Grant of Rights
+Solely within the Applicable Territory, we grant you a non-exclusive, non-transferable, royalty-free, limited license to use, reproduce, distribute, create derivative works (including Model Derivatives), and modify the Materials in accordance with the terms of this Agreement and the Acceptable Use Policy, based on the intellectual property and other rights owned by MiniMax that are embodied in or used by the Materials. You shall not violate (or encourage or permit any person to violate) any term of this Agreement or the Acceptable Use Policy.
+We will continuously evaluate the applicable laws, regulations and compliance requirements for the Excluded Territories. In the meantime, should any person in such Excluded Territories be interested in deploying our models, you are welcome to contact us about obtaining a license, which will be granted based on robust controls and guardrails for purposes of complying with the laws, regulations and compliance requirements of the Excluded Territories.
+III.  Distribution and Redistribution
+Subject to and conditioned on your continuing compliance with this Agreement, including its territorial restrictions and the Acceptable Use Policy, and solely within the Applicable Territory, you may distribute or make available the MiniMax H3 Works to Third Parties within the Applicable Territory; provided, that all of the following conditions are met:
+1. You must provide a copy of this Agreement to all such Third Parties who receive the MiniMax H3 Works or use your products or services related thereto;
+2. You must cause any modified files to carry prominent notices stating that you have modified such files;
+3. You are encouraged to:
+  a. display a notice on any product or service developed using MiniMax H3 indicating that the product or service is “Powered by MiniMax H3”; 
+  b. add an AI-generation identifier to files produced using generative AI models including MiniMax H3; and
+  c. publish at least one technical blog post or a public statement describing your experience using MiniMax H3 Works;
+4. All distributions to Third Parties (other than through Hosted Services) must be accompanied by a “NOTICE” text file containing the following notice:
+  “MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright © 2026 MiniMax. All Rights Reserved.”
+You may add your own copyright notices on your modifications; except as provided in this Section and in Section V, however, you may not impose additional or different terms and conditions on the use, reproduction, or distribution of your modifications or of any aggregate Model Derivatives, and your use, reproduction, modification, distribution, running, and display of the work must otherwise comply with the terms and conditions of this Agreement (including the provisions concerning the Applicable Territory). If you receive the MiniMax H3 Works from a Licensee as part of an integrated end-user product, the provisions of Section III of this Agreement do not apply to you, but Section V and Exhibit A remain applicable.
+IV.  Additional Commercial Terms
+1. You shall obtain a separate, prior written authorization from MiniMax by contacting api@minimax.io with the subject line “MiniMax H3 licensing - authorization request”, if your commercial products and services generate more than 20 million US dollars (or equivalent in other currencies) in yearly revenue.
+2. You shall prominently display “MiniMax H3”on the user interface of commercial product or service that uses MiniMax H3 or MiniMax H3 Works.
+V. Use Restrictions
+1. Your use of the MiniMax H3 Works must comply with applicable laws and regulations (including trade-compliance laws and regulations) and must comply with the Acceptable Use Policy for the MiniMax H3 Works, which is incorporated into this Agreement by reference. 
+2. Before providing access to the MiniMax H3 Works or any product, service, or Hosted Service incorporating them, you must bind each recipient or user to enforceable terms at least as protective as the use restrictions in this Section V and Exhibit A, and you must notify each recipient or user that those restrictions apply.
+3. You may not use the MiniMax H3 Works or any of their Outputs or results to improve any other artificial intelligence model (other than MiniMax H3 or its Model Derivatives).
+4. You may not use, reproduce, modify, distribute, or display the MiniMax H3 Works or any of their Outputs or results outside the Applicable Territory. Any such use outside the Applicable Territory is not authorized by this Agreement.
+5. If you provide or make available to any Third Party a product, service, or Hosted Service that permits the generation of Outputs using MiniMax H3 or any Model Derivative, you must, before making that product or service available and throughout its operation, implement, maintain, test, and periodically review reasonable and proportionate technical and organizational safeguards designed to prevent and mitigate access, uses, and Outputs that violate this Section V or Exhibit A, including uses or Outputs that infringe, misappropriate, or otherwise violate any Third Party’s intellectual-property or other rights. You must not knowingly disable, materially weaken, or permit the circumvention of those safeguards. You must maintain a reasonably accessible mechanism for reporting suspected violations. Upon receiving a good-faith report or otherwise obtaining actual knowledge of a violation, you must promptly investigate and take reasonable steps within your control to stop or mitigate the violation, including removing or disabling access to offending content or services and suspending or terminating repeat violators where appropriate. You are responsible for implementing and enforcing these requirements with respect to your products, services, systems, users, and downstream recipients.
+VI.  Intellectual Property
+1. Subject to MiniMax’s rights in the MiniMax H3 Works (and the intellectual property therein), and to your compliance with the terms and conditions of this Agreement, as between you and MiniMax, you will own the derivative works and modifications of the Materials that you have created or had created, as well as any Model Derivatives.
+2. Except for the limited license expressly granted in this paragraph, no trademark license is granted under this Agreement; with respect to MiniMax H3 Works, the Licensee may not use any name or mark owned by or associated with MiniMax or any of its affiliates, except as reasonably and customarily necessary to describe and distribute the MiniMax H3 Works. MiniMax hereby grants you a license to use the “MiniMax H3” mark (the “Mark”) within the Applicable Territory solely for the purpose of complying with Section III.3; provided, that you comply with all applicable trademark-protection laws. All goodwill arising from your use of the Mark shall inure to the benefit of MiniMax.
+3. If you bring or assert any suit or other legal proceeding (including a cross-claim or counterclaim in any action) against us or any other natural or legal person alleging that the Materials, any Output, or any portion of the foregoing infringes any intellectual property right or other right owned by you or for which you can obtain a license, all licenses granted to you under this Agreement will terminate as of the date such suit or proceeding is filed. You shall defend, indemnify, and hold us harmless against any Third-Party claim arising out of or related to the use or distribution of the MiniMax H3 Works by you or by any Third Party.
+4. MiniMax claims no rights over the Outputs you generate. You and your users are entirely responsible for the Outputs and any subsequent use thereof.
+VII.  Disclaimers and Limitations of Liability
+1. We have no obligation to support, update, provide training for, or develop any further version of the MiniMax H3 Works, or to grant any license with respect thereto.
+2. UNLESS AND ONLY TO THE EXTENT REQUIRED BY APPLICABLE LAW, THE MINIMAX H3 WORKS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED “AS IS” WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES OF ANY KIND INCLUDING ANY WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, COURSE OF DEALING, USAGE OF TRADE, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING, REPRODUCING, MODIFYING, PERFORMING, DISPLAYING OR DISTRIBUTING ANY OF THE MINIMAX H3 WORKS OR OUTPUTS AND ASSUME ANY AND ALL RISKS ASSOCIATED WITH YOUR OR A THIRD PARTY’S USE OR DISTRIBUTION OF ANY OF THE MINIMAX H3 WORKS OR OUTPUTS AND YOUR EXERCISE OF RIGHTS AND PERMISSIONS UNDER THIS AGREEMENT.
+3. TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT SHALL MINIMAX OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, FOR ANY DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, CONSEQUENTIAL OR PUNITIVE DAMAGES, OR LOST PROFITS OF ANY KIND ARISING FROM THIS AGREEMENT OR RELATED TO ANY OF THE MINIMAX H3 WORKS OR OUTPUTS, EVEN IF MINIMAX OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+VIII.  Term and Termination
+1. This Agreement is effective from the moment you accept this Agreement or begin accessing the Materials, and, subject to your compliance with its terms and conditions, will remain in effect until terminated as provided herein.
+2. If you breach any term or condition of this Agreement, we have the right to terminate this Agreement. Upon termination, you must immediately cease accessing, using, and distributing the MiniMax H3 Works; delete or destroy all copies within your possession or control; and notify each downstream recipient that your authorization has ended. The obligations in the preceding sentence and Sections VI.1, VI.3, VII, and IX survive termination.
+IX.  Governing Law and Jurisdiction
+1. This Agreement, and any dispute arising out of or related to this Agreement, shall be governed by the laws of the Hong Kong Special Administrative Region of the People’s Republic of China, without regard to its conflict-of-laws rules. The United Nations Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+2. Any dispute arising out of or related to this Agreement shall be subject to the exclusive jurisdiction of the courts of the Hong Kong Special Administrative Region of the People’s Republic of China with competent jurisdiction. Both MiniMax and the Licensee hereby consent to the exclusive jurisdiction of such courts for any such dispute.
+Additional Note: Please note that the encoder of MiniMax H3 uses Qwen3-VL-32B, which is licensed under Apache 2.0 License: https://github.com/QwenLM/Qwen3-VL/blob/main/LICENSE.
+
+Exhibit A — Acceptable Use Policy
+MiniMax reserves the right to update this Acceptable Use Policy from time to time. 
+Last revised: August 2, 2026.
+MiniMax is committed to promoting the safe and fair use of its tools and features, including MiniMax H3. You agree not to use MiniMax H3, any Model Derivatives, or any Output in any of the following ways:
+1. Use outside the Applicable Territory;
+2. Use in any manner that violates any applicable national, federal, state, local, or international law, regulation, or other legal requirement, or that infringes, misappropriates, or otherwise violates any Third Party’s intellectual-property or other proprietary rights, including through unauthorized reproduction, distribution, public display, public performance, or creation of derivative works;
+3. Use in any manner that may harm yourself or others;
+4. Use to repurpose or distribute the Outputs of MiniMax H3 or any Model Derivatives in order to harm yourself or others;
+5. Use to circumvent or bypass any safety guardrails or safeguards we have implemented;
+6. Use in any manner that exploits or harms, or intends to exploit or harm, minors;
+7. Use to generate or disseminate verifiably false information and/or content for the purpose of harming others or influencing elections;
+8. Use to manufacture or facilitate false online engagement, including fake reviews and other means of false online engagement;
+9. Use to intentionally defame, disparage, or otherwise harass others;
+10. Use to generate and/or disseminate malware (including ransomware) or any other content intended to damage electronic systems;
+11. Use to generate or disseminate personally identifiable information for the purpose of harming others;
+12. Use to generate or disseminate information (including images, code, posts, or articles) in or to any public environment (including via bot tweets or similar means) without clearly and prominently disclosing that such information and/or content is machine-generated;
+13. Use to impersonate another person without that person’s consent, authorization, or lawful right to do so;
+14. Use to make high-risk automated decisions in critical domains that affect individual safety, rights, or well-being (such as law enforcement, immigration, healthcare or medical services, critical-infrastructure management, product-safety components, essential services, credit, employment, housing, education, social scoring, or insurance);
+15. Use in any manner that violates or disregards the social, ethical, or moral standards of other countries or regions;
+16. Use to carry out, assist, threaten, incite, plan, advocate for, or encourage violent extremism or terrorism;
+17. Use for any purpose intended to discriminate against, or harm, individuals or groups based on protected characteristics or categories, online or offline social behavior, or known or predicted personality traits;
+18. Use to intentionally exploit the vulnerabilities of specific populations based on age, social, physical, or psychological characteristics, so as to materially distort the behavior of a member of that group in a manner that causes, or is likely to cause, physical or psychological harm to that person or to others;
+19. Use for military purposes;
+20. Use to engage in any unauthorized or unlicensed professional activity, including but not limited to financial, legal, medical or healthcare, or other professional practice.

base_model/README.md

@@ -0,0 +1,423 @@
+---
+pipeline_tag: image-text-to-video
+license: other
+license_name: minimax-h3-community-license-agreement
+license_link: LICENSE
+library_name: diffusers
+tags:
+  - text-to-video
+  - image-to-video
+  - image-text-to-video
+  - video-to-video
+  - text-to-audio-video
+  - image-to-audio-video
+  - image-text-to-audio-video
+  - video-to-audio-video
+  - audio-to-audio-video
+  - audio-video-generation
+  - multimodal
+  - synchronized-audio-video
+  - reference-to-audio-video
+---
+
+<div align="center">
+  <img width="100%" src="assets/minimax-h3.png" alt="MiniMax">
+</div>
+
+<p align="center">
+  <a href="https://hailuoai.video" target="_blank"><img src="https://img.shields.io/badge/Hailuo%20AI-FF6C37?logo=minimax&logoColor=white" alt="Hailuo AI"></a>
+  <a href="https://platform.minimax.io/docs/guides/text-generation" target="_blank"><img src="https://img.shields.io/badge/API-FF6C37?logo=minimax&logoColor=white" alt="API"></a>
+  <a href="https://www.minimax.io" target="_blank"><img src="https://img.shields.io/badge/MiniMax%20Website-FF6C37?logo=minimax&logoColor=white" alt="MiniMax Website"></a>
+  <a href="https://github.com/MiniMax-AI/MiniMax-H3" target="_blank"><img src="https://img.shields.io/badge/GitHub-181717?logo=github&logoColor=white" alt="GitHub"></a>
+  <a href="https://huggingface.co/MiniMaxAI/MiniMax-H3" target="_blank"><img src="https://img.shields.io/badge/Hugging%20Face-FFD21E?logo=huggingface&logoColor=black" alt="Hugging Face"></a>
+  <br>
+  <a href="https://modelscope.cn/organization/minimax" target="_blank" rel="noopener noreferrer"><img alt="ModelScope MiniMax AI" src="https://img.shields.io/badge/ModelScope-MiniMax%20AI-white?labelColor=%23EF3D5D"></a>
+  <a href="https://platform.minimaxi.com/docs/faq/contact-us" target="_blank"><img src="https://img.shields.io/badge/WeChat-07C160?logo=wechat&logoColor=white" alt="WeChat"></a>
+  <a href="https://discord.com/invite/dbMxutw7tP" target="_blank"><img src="https://img.shields.io/badge/Discord-5865F2?logo=discord&logoColor=white" alt="Discord"></a>
+  <a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE"><img src="https://img.shields.io/badge/LICENSE-4CAF50?logo=creativecommons&logoColor=white" alt="LICENSE"></a>
+</p>
+
+
+# MiniMax H3
+
+## News
+Offical skills to imporve prompt writing: [skills on github](https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills)
+
+## Online API
+Use MiniMax\-H3 directly via API\. 
+- Global: [platform\.minimax\.io](https://platform.minimax.io/docs/api-reference/video-generation-v2-create) \| CN: [platform\.minimaxi\.com](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-create)
+
+## Online App
+Use MiniMax\-H3 directly via App\.
+- WebApp Global: [hailuoai\.video](https://hailuoai.video/tools/minimax-h3) \| CN: [hailuoai\.com](https://hailuoai.com/)
+- Desktop Global: [hub\.minimax\.io](https://hub.minimax.io/) \| CN: [hub\.minimaxi\.com](https://hub.minimaxi.com/)
+
+## System Overview
+MiniMax H3 is a general-purpose, omni-modal generative system. It supports unified understanding of multimodal contexts composed of text, images, video, and audio, and can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. Thanks to its task-generalization-oriented system design, H3 already possesses broad multimodal context understanding and generation capabilities at the pre-training stage, enabling outstanding performance in following complex multimodal instructions.
+
+H3 supports the following input and output specifications:
+
+| Category | Specification |
+|---|---|
+| Output duration | 4–15 seconds |
+| Output aspect ratio | Supports a wide range of aspect ratios, including but not limited to 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16 |
+| Output resolution | Supports various resolution dimensions. The shorter side is set to 768 pixels by default. 2K \| generation can be achieved with H3-Regenerate-2K |
+| Output frame rate | 24 FPS |
+| Output audio | 32 kHz stereo |
+| Supported dialogue languages | Stable support for 11 languages: Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish. Additional languages are also supported to varying degrees |
+
+### Model Variants and Input Specifications
+
+| Model Variant | Input Mode | Specifications |
+|---|---|---|
+| H3-Base-FL2VA | First-and-last-frame mode | Supports zero, one, or two input images. <br><br>- No image input: Text-to-video mode <br>- One image input: First-frame-to-video or last-frame-to-video generation <br>- Two image inputs: First-and-last-frame-to-video generation |
+| H3-Base-Ref2VA | Omni-reference mode | Supports multi-modal reference inputs: <br><br>- **Images:** ≤ 9 images <br>- **Videos:** ≤ 3 clips; each clip must be 2–15 seconds long; total duration ≤ 15 seconds <br>- **Audio:** ≤ 3 clips; audio must be accompanied by image or video input and cannot be used as the sole input; each clip must be 2–15 seconds long; total duration ≤ 15 seconds <br>- **Mixed inputs:** Maximum number of files across all input types is 12 |
+
+![Image](assets/overview.png)
+
+The complete H3 system consists of the following three modules:
+- H3-Context-IR: As inputs become increasingly complex, we build a dedicated system to deeply understand and refine the input multimodal instructions, then convert them into a form that H3 can readily understand—the Context Intermediate Representation—for generation. **H3-Context-IR is critical to the quality of the final output, so we strongly recommend incorporating it into your generation pipeline or following the “Prompting Guidance” to build your own context-processing system.**
+- H3-Base: Generates audio and video based on the H3-Context-IR output, producing results at 768p resolution.
+- H3-Regenerate-2K: Feeds the 768p result together with the original context back into H3 to regenerate the output at 2K resolution. This process leverages both H3’s powerful generative capabilities and the rich information contained in the original context, enabling it to produce high-resolution outputs with more accurate details and greater visual fidelity.
+
+## Model Architecture
+
+### H3\-Context\-IR
+
+H3\-Context\-IR is a hosted preprocessing and orchestration system designed for free\-form multimodal inputs\.
+
+It interprets the relationships among text, images, audio, and reference videos, as well as how these materials relate to the intended generation output\. Its internal workflow includes instruction parsing, cross\-modal association, temporal understanding, and complex logical reasoning\.
+
+H3\-Context\-IR serializes its understanding of the context into a structured representation accepted by H3\-Base\. Without deviating from the user’s original intent, it may also supplement missing or underspecified semantic details where appropriate\.
+
+Because H3\-Context\-IR relies on a multi\-stage workflow and multiple hosted models and services, it is not included in this open\-source release\. We provide an API that enables users to reproduce the behavior of the official workflow\. We also provide detailed tutorials, and developers can follow the **Prompting Guidance** to build their own preprocessing systems\.
+
+For detailed usage instructions, see **Recommended Workflow — Full 2K Workflow**\.
+
+**Safety Guardrails**
+
+User\-submitted text, images and videos, as well as enhanced prompts, are subject to automated moderation\. Content suspected of being unlawful, pornographic, or infringing third\-party rights may be blocked\. We use industry\-standard filtering measures but cannot eliminate false positives or false negatives\. These guardrails do not affect the Licensee’s obligations under the MiniMax H3 Community License, especially those relating to lawful use and use restrictions\.
+
+### H3\-Base
+
+![Image](assets/full-arch.png)
+
+#### Architecture Overview
+
+- H3\-Base encodes different modalities using their corresponding encoders or VAEs and organizes the encoded representations into a unified packed multimodal sequence\. RoPE is used to capture the necessary spatial and temporal relationships among tokens before the entire sequence is passed to the H3\-Omni\-Transformer\.
+
+- Specifically, text is encoded by the H3\-Encoder; visual inputs are encoded by both the H3\-Encoder and the H3\-VisualVAE; and audio is encoded solely by the H3\-AudioVAE\.
+
+- The H3\-Omni\-Transformer jointly predicts video and audio latents, which are then decoded into video and stereo audio, respectively\.
+
+- To reduce the computational cost of long multimodal sequences, H3 natively supports sparse\-attention training and inference\. The initial open\-source release provides inference with full attention only\. Our sparse\-attention implementation will be released in a future update\.
+
+#### H3\-Encoder
+
+- The H3\-Encoder uses the full pretrained weights of Qwen3\-VL\-32B and provides the hidden states from its 50th layer to the H3\-Omni\-Transformer\.
+
+- We add several special tokens, such as `<d>`, to the tokenizer configuration\. When using H3, the tokenizer and associated configuration files provided in the H3 repository are required\.
+
+#### H3\-VAE
+
+H3 uses separate visual and audio latents to represent their respective modalities\.
+
+##### H3\-VisualVAE
+
+- H3\-VisualVAE is a temporally causal video autoencoder with a spatial compression factor of 16×, a temporal compression factor of 4×, and 24 latent channels, denoted as f16t4d24\. We apply several latent\-space optimization techniques to jointly improve reconstruction quality and latent learnability\.
+
+- Before being passed to the H3\-Omni\-Transformer, the visual latents are further patchified with a patch size of `1 × 2 × 2` along the `(time, height, width)` dimensions\. As a result, the visual tokens entering the Transformer have an effective spatial downsampling factor of 32×, while the temporal downsampling factor remains 4×\.
+
+- The latent space of H3\-VisualVAE is optimized for both reconstruction quality and ease of learning by the generative model\. After training its encoder, we additionally train a ViT\-based decoder to reduce decoding costs and further improve reconstruction quality\.
+
+##### H3\-AudioVAE
+
+- H3-AudioVAE uses the same encoder and decoder for both the left and right audio channels while processing each channel independently. The decoded channels are then recombined, enabling stereo audio input and output.
+- For each channel, H3-AudioVAE compresses 32 kHz audio into a sequence of latent tokens with a temporal rate of 40 Hz.
+- Inspired by VA-VAE, we optimize the latent space to preserve audio reconstruction quality while making it easier for the generative model to learn.
+
+#### H3\-Omni\-Transformer
+
+- For scalability and generalization, we adopt a relatively simple Transformer block design\. H3\-Omni\-Transformer is a 33B\-parameter dense, single\-stream Transformer, with approximately 13B parameters residing in AdaLN\-related branches\. Because the AdaLN modulation outputs can be precomputed and cached, these parameters do not need to be loaded for inference\-only deployment\. We release the complete model weights to support further development, including fine\-tuning\.
+
+- Neither the attention layers nor the FFN layers contain modality\-specific structures\. Modality\-specific parameters are confined to the input/output layers and the AdaLN branches\. In particular, modality\-specific AdaLN improves generation quality with relatively low additional training and inference costs\.
+
+- The model uses three\-dimensional Multimodal Rotary Position Embeddings \(MM\-RoPE\) to represent positional relationships across the temporal and two spatial dimensions, `(t, h, w)`\.
+
+- During the final stage of training, we introduce native sparse attention to reduce the computational cost of long sequences\. The sparse\-attention implementation is not included in the initial open\-source release and will be published separately in a future update\.
+
+    
+
+### H3-Regenerate-2K
+
+- For H3's 2K\-resolution output, instead of using a conventional dedicated super\-resolution module, we use the H3 base model to regenerate its own low\-resolution result through an in\-context manner\.
+
+- This approach provides two advantages: \(1\) the regeneration process can reuse the generative capabilities of H3 base model to the greatest extent possible; and \(2\) the in\-context format can reuse the original multimodal context when producing high\-resolution output, allowing it to recover information that conventional super\-resolution methods would otherwise have to “guess,” such as small text and fine details\.
+
+- In\-context regeneration is also an example of task generalization\.
+
+- **Due to the complexity of the system, this module is not yet open\-sourced\. We will release it once it is ready\.** We provide an API for validating the official results; see "Full 2K Workflow" below\.
+
+
+
+## Recommended Workflow
+
+To help the community deploy MiniMax H3 correctly, we provide two validation methods\.
+
+Since the complete H3 system consists of three modules—H3\-Context\-IR, H3\-Base, and H3\-Regenerate\-2K—the “Full 2K Workflow” provides an end\-to\-end validation pipeline for 2K output, combining the Open Platform API with a locally deployed H3\-Base\. The “Local Deployment of H3\-Base” section provides a method for validating 768p output using only a locally deployed H3\-Base\.
+
+In addition, the “Prompting Guidance” section provides a detailed tutorial to help the community develop their own prompting systems\.
+
+### Local Deployment of H3\-Base
+
+MiniMax H3 is released as two task\-specific checkpoints\. Each checkpoint contains a specialized Omni Transformer Model together with the required processor, tokenizer, text encoder, Visual VAE, and standalone Audio VAE components\.
+
+|Checkpoint|Supported Tasks|Input Conditions|Output|Precision|
+|---|---|---|---|---|
+|MiniMax\-H3 Base FL2VA|Text\-to\-Audio\-Video \(`t2va`\), First/Last\-Frame\-to\-Audio\-Video \(`fl2va`\)|Text; optional first frame, last frame, or both|Video and audio|BF16|
+|MiniMax\-H3 Base Ref2VA|Reference\-to\-Audio\-Video \(`ref2va`\)|Text with reference images, videos, and/or audio|Video and audio|BF16|
+
+The released checkpoints are CFG-distilled Omni Transformer model weights. 
+
+Each checkpoint is distributed as a self\-contained Hugging Face\-style repository with the following components:
+
+```text
+<TASK>/
+├── model_index.json
+├── processor/
+├── tokenizer/
+├── text_encoder/
+├── transformer/
+├── visual_vae/
+└── audio_vae/
+```
+
+Download the model. The repository hosts the original checkpoint (`FL2VA/`, `Ref2VA/`) and the diffusers format side by side, so scope the download to what your framework needs:
+
+`model_index.json` is the repository-level public entry. The task-family-specific diffusers indexes remain under `FL2VA/model_index.json` and `Ref2VA/model_index.json`.
+
+```bash
+# Original checkpoint, both task families (SGLang, vLLM):
+hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" "Ref2VA/*" --local-dir MiniMax-H3
+
+# Or a single task family:
+hf download MiniMaxAI/MiniMax-H3 --include "model_index.json" "FL2VA/*" --local-dir MiniMax-H3
+```
+
+diffusers users do not need a manual download: `ModularPipeline.from_pretrained("MiniMaxAI/MiniMax-H3")` fetches exactly the components it needs. See the [diffusers documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3) for loading recipes.
+
+We recommend the following inference frameworks to serve the model:
+
+- [SGLang](https://docs.sglang.io/) \- see [cookbook](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3) 
+
+- [vLLM](https://github.com/vllm-project/vllm) \- see [vllm recipes](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3)
+
+- [diffusers](https://github.com/huggingface/diffusers) \- see [diffusers docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3)
+
+- [ComfyUI](https://github.com/Comfy-Org/ComfyUI) \- see  [Comfy tutorial](https://docs.comfy.org/tutorials/video/minimax/minimax-h3); use [R2V template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_minimax_h3_r2v.json) / [T2V template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_minimax_h3_t2v.json)
+
+#### Sglang Deployment
+
+Here we use sglang as a deployment example\. See the [MiniMax\-H3 deployment guide](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3#3-serve-minimax-h3) for additional deployment configurations\.
+
+FL2VA:
+
+```bash
+sglang serve \
+  --model-path MiniMaxAI/MiniMax-H3 \
+  --num-gpus 4 \
+  --ulysses-degree 4 \
+  --performance-mode speed \
+  --host 0.0.0.0 \
+  --port 30010 \
+  --model-variant fl2va
+```
+
+Ref2VA:
+
+```bash
+sglang serve \
+  --model-path MiniMaxAI/MiniMax-H3 \
+  --num-gpus 4 \
+  --ulysses-degree 4 \
+  --performance-mode speed \
+  --host 0.0.0.0 \
+  --port 30011 \
+  --model-variant ref2va
+```
+
+#### Reproducible 768p cases
+
+The following three use cases T2VA, FL2VA, and Ref2VA demonstrate how to reproduce MiniMax\-H3 video\-audio generation\.
+
+| Use case | Request | Result |
+|---|---|---|
+| T2VA | [View script](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/reproducible-768p-t2va-request.sh) | [t2va.mp4](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/t2va.mp4) |
+| FL2VA | [View script](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/reproducible-768p-fl2va-request.sh) | [fl2va.mp4](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/fl2va.mp4) |
+| Ref2VA | [View script](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/reproducible-768p-ref2va-request.sh) | [ref2va.mp4](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/ref2va.mp4) |
+
+### Full 2K\-Workflow
+
+This section explains how to combine a locally deployed SGLang service with the official **H3\-Context\-IR** and **H3\-Regenerate\-2K** APIs to reproduce the quality of 2K videos generated directly by the MiniMax API\.
+Before you begin, configure the SGLang endpoint and your MiniMax API credentials:
+
+```bash
+# URL of your SGLang deployment
+SGLANG_DEPLOYMENT_URL="<sglang-deployment-url>"
+
+# MiniMax API endpoint (choose one)
+# CN
+MINIMAX_API_BASE="https://api.minimaxi.com"
+# Global
+# MINIMAX_API_BASE="https://api.minimax.io"
+
+# API token obtained from the MiniMax platform
+TOKEN="<token>"
+```
+
+MiniMax platform:
+
+API docs:
+- Create H3-2K: use /video-generation-v2-create [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-create), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-create)
+- H3-Context-IR：use /video-generation-v2-h3-context-ir [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-h3-context-ir), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-h3-context-ir)
+- H3-Regenerate-2K：use /video-generation-v2-regeneration [EN-docs](https://platform.minimax.io/docs/api-reference/video-generation-v2-regeneration), [CN-docs](https://platform.minimaxi.com/docs/api-reference/video-generation-v2-regeneration)
+
+
+The examples below encode local H3\-Base output files as Base64 Data URLs\. For production use, uploading the video to a publicly accessible URL and passing that URL as `base_video` is recommended\.
+
+For each case below, we provide reference outputs at both 2K and 768p generated directly through the Open Platform API, making it easier to validate the results\.
+
+#### case\-T2VA
+
+- Type: Text-to-video
+- Duration: 10 seconds
+- Aspect ratio: 16:9
+
+<table>
+  <thead>
+    <tr><th>stage</th><th>request</th><th>result</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>H3-Context-IR</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-h3-context-ir.sh">View script</a></td><td><pre><code class="language-json">{
+  &quot;task&quot;: {
+    &quot;id&quot;: &quot;&lt;task_id&gt;&quot;,
+    &quot;model&quot;: &quot;MiniMax-H3&quot;,
+    &quot;status&quot;: &quot;succeeded&quot;,
+    &quot;created_at&quot;: &quot;&lt;created_at&gt;&quot;,
+    &quot;updated_at&quot;: &quot;&lt;updated_at&gt;&quot;,
+    &quot;content&quot;: {
+      &quot;prompt&quot;: &quot;integrated_multimodal_description: [Shot 1] Cinematic, medium wide shot, pushing in slowly. In the cavernous, dimly lit bridge of a starship, sleek metallic consoles with glowing amber displays flank a massive, curved observation window. A female captain, in her late 40s with an athletic build and short silver-streaked black hair, stands in the center midground. She wears a structured, high-collared dark navy military tunic with silver chest insignias. Her back is to the camera, silhouetted against the cool, ambient starlight pouring through the thick glass. She stands perfectly still with her hands clasped tightly behind her back. Outside the window, a massive armada of jagged, dark grey dreadnoughts hovers in tight formation against a deep purple space nebula. The fleet&#39;s massive rear thrusters begin to glow with an intense, escalating bright blue light. [Shot 2] At 00:04.500, the camera cuts to a close-up of the captain&#39;s face and shakes strongly. The brilliant blue-white light from the fleet&#39;s gathering energy reflects vividly in her dark eyes. Suddenly, a blinding white flash floods through the window, completely washing out the background as the fleet jumps to hyperspace. The sheer spatial force violently jolts the bridge, causing the captain from Shot 1 to stagger slightly forward, her shoulders tensing as she visibly braces herself against the physical tremors. As the intense white light fades abruptly, leaving only the dim, empty expanse of the purple nebula reflected on her starkly lit skin, her jaw clenches, and she slowly closes her eyes in the newly emptied space.\noverall_soundscape: A low, resonant hum of the ship&#39;s ambient life support systems serves as the baseline, soon drowned out by an audible, escalating, high-pitched electronic whine as the fleet outside charges its hyperdrives. A massive, deafening, bass-heavy boom and sharp crackle erupts during the blinding flash, accompanied by the loud metallic creaking, rattling, and deep thuds of the bridge&#39;s bulkheads vibrating under immense physical stress. The intense roaring impact then cuts abruptly back to a hollow, echoing room tone, leaving only the faint, steady hum of the isolated bridge.\nnon_diegetic_music: Cinematic space-opera orchestral score, slow tempo, featuring a solitary, mournful French horn melody over deep, sustained string dissonances that build rapidly in volume and intensity, swelling to a massive orchestral peak before snapping immediately into silence right after the jump.&quot;
+    },
+    &quot;duration&quot;: 10,
+    &quot;usage&quot;: {
+      &quot;total_tokens&quot;: 8565,
+      &quot;prompt_tokens&quot;: 5650,
+      &quot;completion_tokens&quot;: 2915
+    },
+    &quot;ratio&quot;: &quot;16:9&quot;,
+    &quot;task_type&quot;: &quot;h3_context_ir&quot;,
+    &quot;modality&quot;: &quot;text&quot;
+  }
+}</code></pre></td></tr>
+    <tr><td>H3-Base</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-h3-base.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/t2va.mp4">t2va.mp4</a></td></tr>
+    <tr><td>H3-Regenerate-2K</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-h3-regenerate-2k.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/t2va_2k.mp4">t2va_2k.mp4</a></td></tr>
+    <tr><td>Reference 2K result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-reference-2k-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/h3_direct_2k.mp4">h3_direct_2k.mp4</a></td></tr>
+    <tr><td>Reference 768P result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-t2va-reference-768p-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/h3_direct_768p.mp4">h3_direct_768p.mp4</a><br></td></tr>
+  </tbody>
+</table>
+
+#### case\-I2VA
+
+- Type: First-frame image-to-video
+- Duration: 8 seconds
+- Aspect ratio: adaptive
+
+<table>
+  <thead>
+    <tr><th>stage</th><th>request</th><th>result</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>H3-Context-IR</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-h3-context-ir.sh">View script</a></td><td><pre><code class="language-json">{
+  &quot;task&quot;: {
+    &quot;id&quot;: &quot;&lt;task_id&gt;&quot;,
+    &quot;model&quot;: &quot;MiniMax-H3&quot;,
+    &quot;status&quot;: &quot;succeeded&quot;,
+    &quot;created_at&quot;: &quot;&lt;created_at&gt;&quot;,
+    &quot;updated_at&quot;: &quot;&lt;updated_at&gt;&quot;,
+    &quot;content&quot;: {
+      &quot;prompt&quot;: &quot;For the target video, at 0.00 seconds into the target video, &lt;Picture 1&gt; (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] This is a live-action, cinematic shot with a shallow depth of field. The camera holds a perfectly static shot throughout the entire eight-second duration, capturing a cozy family gathering in a traditional Japanese dining room. The scene opens with a large, intricately patterned blue and white ceramic bowl of ramen in the immediate foreground, rendered in crisp, sharp focus. The bowl sits on a smooth, polished long wooden table. Inside the bowl, a rich, oily golden-brown broth surrounds yellow wavy noodles, topped with two thick, round slices of chashu pork featuring visible fat marbling and a distinct spiral meat pattern. A generous mound of freshly chopped, bright green scallions rests in the center, and a crisp, dark green rectangular sheet of nori seaweed is tucked into the right edge. To the left of the bowl, a pair of light brown wooden chopsticks rests horizontally on a small, dark rectangular chopstick rest, near a small cylindrical ceramic teacup with blue painted patterns. On the right side of the table, a spherical paper lantern with a ribbed bamboo frame sits on a black wooden base. In the background, a large family of seven is gathered around the table, initially appearing as a soft, blurred presence. Behind them, traditional Japanese sliding shoji screens with wooden lattice frames are open, revealing a bright outdoor scene with lush green trees. Early in the clip, the thick, white steam rising from the hot ramen broth immediately intensifies, billowing upwards in thick, swirling clouds that dance continuously above the bowl. As the clip progresses into the middle seconds, the camera maintains its static position while the focus begins a deliberate, smooth shift deeper into the room. The foreground ramen bowl, its vibrant ingredients, and the rising steam gradually soften into a hazy, out-of-focus blur. Simultaneously, the family members in the background come into sharp, detailed clarity. The heavy steam continues to rise from the foreground, creating a dynamic, translucent veil between the camera and the family. With the focus now firmly locked on the background, the vibrant family dinner comes alive. The man in the dark navy blue long-sleeved shirt on the left leans forward, his mouth moving animatedly in a silent exchange. The young girl in the crisp white short-sleeved t-shirt beside him smiles brightly, looking toward the center of the table. The woman on the far left, wearing a soft light blue long-sleeved blouse, turns her head slightly, smiling gently. Across the table, the woman in the light grey button-down shirt smiles broadly, her eyes crinkling, as she rests her hands near her plate. The woman in the dark grey top further back uses her wooden chopsticks to pick up a small piece of food from a central ceramic dish filled with bright red pickled vegetables. The woman in the center back in the light grey sweater smiles gently, her hands clasped softly in front of her, observing the interaction. Throughout the remainder of the clip, the family continues their lively physical interaction, their mouths moving in continuous, silent cadences of conversation, while the thick, white steam from the blurred ramen bowl in the foreground never stops rising, adding a comforting atmosphere to the warm gathering.\n\noverall_soundscape: The soundscape begins with a quiet room tone mixed with the faint, airy rustle of the thick steam billowing from the hot ramen bowl in the foreground, accompanied by the subtle, continuous hissing and bubbling of the rich broth. As the visual focus shifts deeper into the room, the physical sounds of the bustling family dinner become dominant in the foreground. The clear, sharp clinking of ceramic bowls and wooden chopsticks touching plates is clearly heard as the family members reach for food. This is followed by the faint, muffled thud of a cup being set down on the smooth wooden table, and the subtle, rhythmic rustle of cotton and wool clothing as the family members lean forward and gesture, perfectly capturing the lively, physical atmosphere of the shared meal.\n\nnon_diegetic_music: A gentle, heartwarming acoustic guitar melody plays softly in the background, accompanied by the subtle, resonant notes of a traditional Japanese koto. The music maintains a slow, comforting tempo that enhances the cozy, nostalgic, and joyful atmosphere of the family gathering.&quot;
+    },
+    &quot;duration&quot;: 8,
+    &quot;usage&quot;: {
+      &quot;total_tokens&quot;: 22822,
+      &quot;prompt_tokens&quot;: 12800,
+      &quot;completion_tokens&quot;: 10022
+    },
+    &quot;ratio&quot;: &quot;16:9&quot;,
+    &quot;task_type&quot;: &quot;h3_context_ir&quot;,
+    &quot;modality&quot;: &quot;text&quot;
+  }
+}</code></pre></td></tr>
+    <tr><td>H3-Base</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-h3-base.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/i2va.mp4">i2va.mp4</a></td></tr>
+    <tr><td>H3-Regenerate-2K</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-h3-regenerate-2k.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/i2va_2k.mp4">i2va_2k.mp4</a><br></td></tr>
+    <tr><td>Reference 2K result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-reference-2k-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/i2va_direct_2k.mp4">i2va_direct_2k.mp4</a></td></tr>
+    <tr><td>Reference 768P result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-i2va-reference-768p-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/i2va_direct_768p.mp4">i2va_direct_768p.mp4</a></td></tr>
+  </tbody>
+</table>
+
+#### case\-Ref2VA
+
+- Type: Multimodal reference-to-video (video + audio)
+- Duration: 5 seconds
+- Aspect ratio: adaptive
+
+<table>
+  <thead>
+    <tr><th>stage</th><th>request</th><th>result</th></tr>
+  </thead>
+  <tbody>
+    <tr><td>H3-Context-IR</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-h3-context-ir.sh">View script</a></td><td><pre><code class="language-json">{
+  &quot;task&quot;: {
+    &quot;id&quot;: &quot;&lt;task_id&gt;&quot;,
+    &quot;model&quot;: &quot;MiniMax-H3&quot;,
+    &quot;status&quot;: &quot;succeeded&quot;,
+    &quot;created_at&quot;: &quot;&lt;created_at&gt;&quot;,
+    &quot;updated_at&quot;: &quot;&lt;updated_at&gt;&quot;,
+    &quot;content&quot;: {
+      &quot;prompt&quot;: &quot;subject_definitions:\n&lt;Subject 1&gt; is the young man with short wavy blonde hair, wearing a bright pink suit jacket, matching pink trousers, an unbuttoned white shirt, and silver rings, holding a small black lamb in his arms in &lt;Video 1&gt;.\n&lt;Video 1&gt; is the source video for the editing task.\n&lt;Audio 1&gt; is the synchronized audio track of &lt;Video 1&gt;, providing the background music.\n&lt;Audio 2&gt; is the voice timbre reference for &lt;Subject 1&gt;&#39;s voice, containing a spoken male voiceover.\n\nsummary:\n[video editing + audio reference + audio reuse] The target video is an edited version of &lt;Video 1&gt;. &lt;Subject 1&gt;, wearing a bright pink suit and holding a black lamb, stands in a grassy field with other white lambs in the background. The edit animates &lt;Subject 1&gt;&#39;s face to speak the user-provided dialogue. &lt;Audio 1&gt; is partially reused as the continuous background music, while the target references the calm male voice timbre of &lt;Audio 2&gt; for &lt;Subject 1&gt;&#39;s spoken lines.\n\nretention_analysis:\n&lt;Subject 1&gt; (appears in [Shot 1]): fully_preserved - the man retains his identity, wavy blonde hair, pink suit, white shirt, accessories, and the black lamb he holds, with his mouth newly animated to speak.\n&lt;Video 1&gt; (source video editing): fully_preserved - the original camera framing, warm golden hour lighting, grassy hill setting, and background white lambs are maintained while the central character is edited.\n&lt;Audio 1&gt;: partially_copy - the atmospheric background music from &lt;Audio 1&gt; is reused in the target video, mixed beneath the newly added spoken dialogue.\n&lt;Audio 2&gt;: reference - the target audio references the male voice timbre from &lt;Audio 2&gt; to generate &lt;Subject 1&gt;&#39;s spoken dialogue.\n\ndetailed_description:\nThe target video is in realistic photographic style.\n[Shot 1] The shot begins from the source &lt;Video 1&gt;, showing &lt;Subject 1&gt;, a young man with short wavy blonde hair, wearing a bright pink suit jacket, matching pink trousers, and a casually unbuttoned white shirt. He stands confidently in a sunlit green pasture, gently holding a small black lamb securely in his arms. The warm, golden hour lighting casts soft shadows across his face and the bright pink fabric of his suit. Behind him, several white lambs stand and graze on the rolling grassy hill against a clear, pale blue sky. The atmospheric background music from &lt;Audio 1&gt; plays continuously throughout the scene. &lt;Subject 1&gt; physically speaks, his mouth movements naturally syncing to the new dialogue, with his voice timbre referencing the calm male delivery from &lt;Audio 2&gt;. Looking thoughtfully forward, &lt;Subject 1&gt; (S1) speaks softly, &lt;d&gt;[English] Follow the wind, live free.&lt;/d&gt; As he delivers the line, he subtly shifts his weight, cradling the resting black lamb while the camera slowly pushes in. &lt;Subject 1&gt; (S1) continues his thought, &lt;d&gt;[English] Leave worries behind, enjoy the moment.&lt;/d&gt; Exactly as his voice stops, his lips meet in a relaxed, peaceful smile, and his jaw ceases speaking motion. He then turns his gaze slightly away toward the horizon, gently stroking the black lamb&#39;s fleece with his fingers as the camera holds on this tranquil, sunlit state through the end of the video.\n\noverall_soundscape:\nThe soundscape consists of the continuous, atmospheric background music from &lt;Audio 1&gt;, overlaid with the clear, calm male dialogue spoken by the main character, referencing the voice timbre of &lt;Audio 2&gt;.\n\nnon_diegetic_music:\nThe atmospheric, sustained background music from &lt;Audio 1&gt; is reused as the continuous score, playing quietly beneath the spoken dialogue.&quot;
+    },
+    &quot;duration&quot;: 5,
+    &quot;usage&quot;: {
+      &quot;total_tokens&quot;: 39299,
+      &quot;prompt_tokens&quot;: 33323,
+      &quot;completion_tokens&quot;: 5976
+    },
+    &quot;ratio&quot;: &quot;16:9&quot;,
+    &quot;task_type&quot;: &quot;h3_context_ir&quot;,
+    &quot;modality&quot;: &quot;text&quot;
+  }
+}</code></pre></td></tr>
+    <tr><td>H3-Base</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-h3-base.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/r2va.mp4">r2va.mp4</a><br></td></tr>
+    <tr><td>Reference 2K result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-reference-2k-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/r2va_2k.mp4">r2va_2k.mp4</a></td></tr>
+    <tr><td>H3 API 2K in Open Platform for reference</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-h3-api-2k-in-open-platform-for-reference.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/r2va_direct_2k.mp4">r2va_direct_2k.mp4</a><br></td></tr>
+    <tr><td>Reference 768P result by directly calling Open Platform API</td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/scripts/readme/full-2k-ref2va-reference-768p-result-by-directly-calling-open-platform-api.sh">View script</a></td><td><a href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/assets/r2va_direct_768p.mp4">r2va_direct_768p.mp4</a><br></td></tr>
+  </tbody>
+</table>
+
+### Prompting Guidance
+
+[VIDEO\_PROMPT\_WRITING\_GUIDE\_base\_en\.md](docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md)
+
+[VIDEO\_PROMPT\_WRITING\_GUIDE\_ref\_en\.md](docs/VIDEO_PROMPT_WRITING_GUIDE_ref_en.md)
+
+skills to improve prompt: https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills
+
+## License
+
+- MiniMax H3 is released under the [MiniMax H3 Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE).
+- [Q&A about the License](docs/QA-about-License.md)
+- [Application form(only for USA/EU/UK/South Korea)](https://platform.minimax.io/h3-license)
+
+## Contact Us
+
+Contact us at [model@minimax.io](mailto:model@minimax.io).

base_model/audio_scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "MiniMaxH3Scheduler",
+  "_diffusers_version": "0.36.0.dev0",
+  "shift": 3.0
+}

base_model/audio_vae/config.json

@@ -0,0 +1,125 @@
+{
+  "_class_name": "AutoencoderKLMiniMaxH3Audio",
+  "_diffusers_version": "0.36.0.dev0",
+  "encoder_dim": 64,
+  "encoder_rates": [
+    2,
+    4,
+    4,
+    5,
+    5
+  ],
+  "latent_dim": 2048,
+  "latent_channels": 32,
+  "decoder_dim": 1024,
+  "decoder_rates": [
+    5,
+    5,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_kernel_sizes": [
+    9,
+    9,
+    4,
+    4,
+    4,
+    4,
+    4
+  ],
+  "num_attention_heads": 8,
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "sampling_rate": 32000,
+  "latents_mean": [
+    -0.020211687488382354,
+    0.3876466479950502,
+    -0.04398279799186767,
+    -0.28591514936373,
+    0.08179686214561671,
+    -0.35782641352446604,
+    0.040623809960919084,
+    -0.01552534501956604,
+    -0.223362481667332,
+    0.1821006842509091,
+    0.2941778783780663,
+    -0.07901167601970885,
+    -0.056815072777201,
+    -0.3699028221860095,
+    -0.31616315591624855,
+    0.5905951377425391,
+    -0.052139568068853864,
+    0.013673160263486295,
+    -0.03691647864630577,
+    0.09732660653298163,
+    -0.3394662328788498,
+    -0.30685677538541667,
+    -0.24504598907458763,
+    -0.034698524462007344,
+    0.02868032184767538,
+    -0.21217779266454084,
+    -0.1678263169941987,
+    0.3221287889040614,
+    -0.1223055851554907,
+    0.4356604928128464,
+    -0.0502599202236253,
+    0.3979258376211797
+  ],
+  "latents_std": [
+    1.6895524230479284,
+    2.76263727217653,
+    1.7945344281264435,
+    1.6801681847309828,
+    1.6390226546605453,
+    2.7788298348882177,
+    1.7659090095747236,
+    1.6199757612137327,
+    2.6336525640336896,
+    1.8539356672817833,
+    2.5056497896915633,
+    1.811019237886178,
+    1.9579657790720237,
+    1.6685498243529284,
+    1.4922469314453364,
+    3.298670198067373,
+    1.9491804496832168,
+    1.8720003270431442,
+    1.8334080103291832,
+    1.6488070416529093,
+    1.6176957696319716,
+    1.9131449234774398,
+    1.5695245398428617,
+    1.6943659940415912,
+    1.8318420762504692,
+    1.5540637421583379,
+    1.9344930328968526,
+    1.599198216109855,
+    1.718045989838149,
+    1.6307219190837705,
+    1.8661226051202384,
+    1.5613768203168363
+  ]
+}

base_model/audio_vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c59e67ba8de5477c81bfbced0327aabf500f1bfdeefd5ee754529241cb26cb
+size 605429340

base_model/model_index.json

@@ -0,0 +1,131 @@
+{
+  "_class_name": "MiniMaxH3ModularPipeline",
+  "_diffusers_version": "0.36.0.dev0",
+  "_blocks_class_name": "MiniMaxH3Blocks",
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLForConditionalGeneration",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3VLForConditionalGeneration"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "text_encoder",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen2TokenizerFast"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "tokenizer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3VLProcessor"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "processor",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3Audio",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3Audio"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "audio_vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "transformer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "transformer_ref": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "transformer_ref",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "audio_scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "audio_scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ]
+}

base_model/modular_model_index.json

@@ -0,0 +1,131 @@
+{
+  "_class_name": "MiniMaxH3ModularPipeline",
+  "_diffusers_version": "0.36.0.dev0",
+  "_blocks_class_name": "MiniMaxH3Blocks",
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLForConditionalGeneration",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3VLForConditionalGeneration"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "text_encoder",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2TokenizerFast",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen2TokenizerFast"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "tokenizer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "processor": [
+    "transformers",
+    "Qwen3VLProcessor",
+    {
+      "type_hint": [
+        "transformers",
+        "Qwen3VLProcessor"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "processor",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLMiniMaxH3Audio",
+    {
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLMiniMaxH3Audio"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "audio_vae",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "transformer",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "transformer_ref": [
+    "diffusers",
+    "MiniMaxH3Transformer3DModel",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Transformer3DModel"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "transformer_ref",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ],
+  "audio_scheduler": [
+    "diffusers",
+    "MiniMaxH3Scheduler",
+    {
+      "type_hint": [
+        "diffusers",
+        "MiniMaxH3Scheduler"
+      ],
+      "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
+      "subfolder": "audio_scheduler",
+      "variant": null,
+      "revision": null
+    }
+  ]
+}

base_model/processor/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

base_model/processor/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

base_model/processor/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

base_model/processor/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

base_model/scheduler/scheduler_config.json

@@ -0,0 +1,5 @@
+{
+  "_class_name": "MiniMaxH3Scheduler",
+  "_diffusers_version": "0.36.0.dev0",
+  "shift": 12.0
+}

base_model/text_encoder/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

base_model/text_encoder/config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 25600,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

base_model/text_encoder/model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9dfbc930e505402ae9d7e5091a9d7d656cda5f34614f01cfe70bfb0cca27cb
+size 4932328944

base_model/text_encoder/model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bb44b4ff303fe76fe9e894022fb3dc71b15a2e716592790fe0e3c3e60478fa
+size 4875990528

base_model/text_encoder/model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f22e8b3168f8dc962fac0d313607ebf52a12b433d4cf3098a0d82d9f042940
+size 4875990552

base_model/text_encoder/model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad09c74d3c13ee29b5d0d84548fd8a3424a651564eaccd519946c296e59c557f
+size 4875990584

base_model/text_encoder/model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc993c8a0e2a5b0570f383e1a95dc3a1281d1b224b6f3ee908f4827941e1dfc2
+size 4875990584

base_model/text_encoder/model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f05620d1f718a90c362b221d6a184ff1a0f53301d706882d3df49695fa1974
+size 4875990584

base_model/text_encoder/model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb91da8cb01ff4de3eef0eab1c3e769a734b3a1aafc61734068638a0d6c86934
+size 4875990584

base_model/text_encoder/model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431ca56535c8781944ce3801f5eb61c45531e853ecc5846d936ebaf4761b764f
+size 4875990584

base_model/text_encoder/model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3825e3f4302f4d2f7d76aa7430d2ce0864fde6b9e540a5806bf0d8e38e4d9f47
+size 4875990584

base_model/text_encoder/model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aded5a4d1d5e22dbd8b6f79266b6eb88c840411b09527c53917a1419ace22e2f
+size 4875990584

base_model/text_encoder/model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3820ffe8d8d6477f6fe8d614ef3c87abb264ee39accebf43a1507b970d80946f
+size 4875990584

base_model/text_encoder/model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ad2d08ce71963121c9b03f1d9ec5d7641052f4b23c6c12b80d71065eb8e98e
+size 4875990584

base_model/text_encoder/model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64f2289871261fdd1abbd3b78bcd66011b341de3dc8eeb2ed1a473ee7c8d95c
+size 4875990584

base_model/text_encoder/model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45b6c9998c77ee5a6577f9f47bc76416c1d4d387169e50c4c9d3134ea51b13b
+size 3270697008

base_model/text_encoder/model.safetensors.index.json

@@ -0,0 +1,1065 @@
+{
+  "metadata": {
+    "total_size": 66714780128
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.language_model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.language_model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.language_model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.language_model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.58.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.language_model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.language_model.layers.63.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.language_model.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00014-of-00014.safetensors",
+    "model.visual.merger.norm.bias": "model-00014-of-00014.safetensors",
+    "model.visual.merger.norm.weight": "model-00014-of-00014.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00014-of-00014.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00014-of-00014.safetensors",
+    "model.visual.pos_embed.weight": "model-00014-of-00014.safetensors"
+  }
+}

base_model/text_encoder/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

base_model/text_encoder/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

base_model/text_encoder/video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}

base_model/tokenizer/tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>",
+    "<d>",
+    "</d>",
+    "<|cutoff|>",
+    "<|lyrics_start|>",
+    "<|lyrics_end|>",
+    "<|caption_start|>",
+    "<|caption_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

base_model/transformer/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "MiniMaxH3Transformer3DModel",
+  "_diffusers_version": "0.36.0.dev0",
+  "num_attention_heads": 56,
+  "attention_head_dim": 128,
+  "hidden_size": 5376,
+  "num_layers": 50,
+  "num_refiner_layers": 2,
+  "ffn_dim": 14336,
+  "in_channels": 24,
+  "audio_in_channels": 32,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "text_dim": 5120,
+  "freq_dim": 256,
+  "time_embed_hidden_dim": 5376,
+  "time_embed_dim": 2688,
+  "rope_freq_dim": 16,
+  "rope_theta": 10000.0,
+  "norm_eps": 1e-05,
+  "qk_norm_eps": 1e-05,
+  "final_norm_eps": 1e-05
+}

base_model/transformer/diffusion_pytorch_model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d847200c45c09dd7f973c1b096663068408ef851ee0b3711d059b6dc5dcd028
+size 4825958704

base_model/transformer/diffusion_pytorch_model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4d362eddd2802180ac9c744849eb9ba8d9c8b984bdf9822cb02ed004b29184
+size 4702158032

base_model/transformer/diffusion_pytorch_model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949c5aafbbfa5654da730a6a7fafd75adb164d0857b095a30e8bb6d390887d69
+size 4933368192

base_model/transformer/diffusion_pytorch_model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef7616790105ee839766bb2027203bf2c0d87c6aa038dca84145a8675f5ce28
+size 4567069608