Add files using upload-large-folder tool

.gitattributes

@@ -5,6 +5,7 @@
 *.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +34,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/paper-figure-openmle-framework.png filter=lfs diff=lfs merge=lfs -text
+assets/paper-figure-main-results.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,20 @@
+Creative Commons Attribution-NonCommercial 4.0 International
+CC BY-NC 4.0
+
+Copyright (c) 2026 Frontis AI and the OpenMLE contributors.
+
+Except for third-party material identified in NOTICE, the Frontis-MA1 model weights, configuration changes, and documentation distributed in this repository are licensed under the Creative Commons Attribution-NonCommercial 4.0 International Public License.
+
+You may share and adapt the licensed material provided that you:
+
+1. give appropriate credit, provide a link to the license, and indicate if changes were made; and
+2. do not use the licensed material for commercial purposes.
+
+The canonical license and full legal code are available at:
+
+https://creativecommons.org/licenses/by-nc/4.0/
+https://creativecommons.org/licenses/by-nc/4.0/legalcode
+
+SPDX-License-Identifier: CC-BY-NC-4.0
+
+This notice is a convenient repository-level pointer. If it conflicts with the full legal code, the full legal code controls. Upstream material remains subject to the terms and notices identified in NOTICE and LICENSE-UPSTREAM-APACHE-2.0.

LICENSE-UPSTREAM-APACHE-2.0

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

NOTICE

@@ -0,0 +1,8 @@
+Frontis-MA1-35B
+Copyright 2026 Frontis AI and the OpenMLE contributors.
+
+This model is derived from Qwen3.6-35B-A3B, which is Copyright 2026 Alibaba Cloud and licensed under the Apache License 2.0.
+
+The language-model weights contain modifications produced through execution-grounded supervised fine-tuning and reinforcement learning. The vision encoder and MTP components are inherited unchanged from Qwen3.6-35B-A3B to provide a complete, base-compatible release. See README.md for the model lineage, component scope, intended use, evaluation scope, and limitations.
+
+Original Frontis-MA1 material is released under CC BY-NC 4.0 as stated in LICENSE. The upstream Apache License 2.0 text is preserved in LICENSE-UPSTREAM-APACHE-2.0; that upstream notice is not replaced by the Frontis-MA1 license.

README.md

@@ -1,3 +1,287 @@
 ---
 license: cc-by-nc-4.0
+base_model: Qwen/Qwen3.6-35B-A3B
+base_model_relation: finetune
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+  - openmle
+  - frontis-ma1
+  - machine-learning-engineering
+  - autoresearch
+  - agent
+  - coding
+  - qwen3
+  - qwen3.6
+  - moe
+  - multimodal
+  - post-training
 ---
+
+<p align="center">
+  <img src="assets/frontis-logo.png" width="360" alt="Frontis AI">
+</p>
+
+<h1 align="center">Frontis-MA1-35B</h1>
+
+<p align="center">
+  <b>An execution-grounded model for evolutionary machine learning engineering and AutoResearch</b>
+</p>
+
+<p align="center">
+  <a href="#paper-and-citation">📄 Paper</a>
+  &nbsp;•&nbsp;
+  <a href="https://github.com/rc314159-creator/OpenRSI">💻 Code</a>
+  &nbsp;•&nbsp;
+  <a href="https://rc314159-creator.github.io/OpenRSI/">🌐 Project</a>
+  &nbsp;•&nbsp;
+  <a href="https://huggingface.co/FrontisAI">🤗 Models</a>
+  &nbsp;•&nbsp;
+  <a href="https://huggingface.co/datasets/FrontisAI/OpenMLE-Tasks">🧩 Tasks</a>
+  &nbsp;•&nbsp;
+  <a href="https://huggingface.co/datasets/FrontisAI/OpenMLE-SFT-Traces">📚 SFT Traces</a>
+</p>
+
+## Introduction
+
+**Frontis-MA1-35B** is the flagship open-weight research model released with **OpenMLE**, an execution-grounded system for studying meta-evolution in machine learning engineering (MLE).
+
+Starting from [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B), we apply execution-grounded supervised fine-tuning and reinforcement learning so that the model learns four reusable program-transformation operators:
+
+- **Draft** — create a complete initial solution;
+- **Improve** — refine a parent program using its score and execution evidence;
+- **Debug** — repair invalid or failing code;
+- **Crossover** — recombine useful elements from two parent solutions.
+
+At inference time, OpenMLE-Evo composes these operators into a long-horizon search loop. Frontis-MA1 is therefore both a product of the OpenMLE training stack and the model that drives its evolutionary search.
+
+> **Component composition.** The Frontis-MA1 checkpoint contains the
+> post-trained language-model weights used by OpenMLE. For a complete,
+> base-compatible release, this repository also includes the unchanged vision
+> encoder and MTP components from Qwen3.6-35B-A3B. OpenMLE post-training and the
+> reported evaluations are text/code-only; they do not establish improved or
+> fully validated visual capability or MTP decoding quality.
+
+## Highlights
+
+- **Execution-grounded post-training.** SFT examples and RL rewards are constructed from programs executed in isolated MLE sandboxes.
+- **Trainable evolutionary operators.** Draft, Improve, Debug, and Crossover provide a shared action space across training and test-time search.
+- **Linked research release.** The model card connects the weights to the OpenMLE training code, search protocol, task environments, and evaluation boundary.
+- **Strong controlled model gain.** Under the same OpenMLE-Evo harness on MLE-Bench Lite, Frontis-MA1-35B improves Medal Average from **39.39% to 60.61%** and Human Rank from **0.5828 to 0.7647** over its base model.
+- **Composable search gain.** With OpenMLE-Evo-Max, the model–harness system reaches **71.21% Medal Average** and **0.8126 Human Rank** under the paper's fixed evaluation protocol.
+
+> The reported scores measure **model–harness systems**, not standalone one-shot generation. Reproduction requires the same OpenMLE-Evo or OpenMLE-Evo-Max configuration, task environments, sandbox budget, and evaluation protocol.
+
+## Model family
+
+| Model | Base model | Release format | Status |
+| --- | --- | --- | --- |
+| [Frontis-MA1-30B](https://huggingface.co/FrontisAI/Frontis-MA1-30B) | Qwen3-30B-A3B-Thinking-2507 | BF16 Transformers | Companion release |
+| **Frontis-MA1-35B** | Qwen3.6-35B-A3B | BF16 Transformers | This repository |
+| [Frontis-MA1-35B-GGUF](https://huggingface.co/FrontisAI/Frontis-MA1-35B-GGUF) | Frontis-MA1-35B | Q4_K_M GGUF + F16 mmproj | Local deployment |
+
+## Model details
+
+| Field | Value |
+| --- | --- |
+| Model family | Frontis-MA1 |
+| Architecture | Multimodal conditional-generation model with a hybrid-attention MoE text backbone |
+| Parameters | 35B total, approximately 3B activated |
+| Layers | 40 |
+| Experts | 256 routed experts; 8 routed plus 1 shared expert activated per token |
+| Weight precision | BF16 |
+| Native configuration context | 262,144 tokens |
+| Post-training SFT cutoff | 32,768 tokens |
+| Primary evaluated modality | Text and code |
+| Vision encoder | Included; inherited unchanged from Qwen3.6-35B-A3B |
+| MTP weights | Included; inherited unchanged from Qwen3.6-35B-A3B |
+| License | CC BY-NC 4.0 |
+
+The 262,144-token context length is inherited from the base-model configuration. OpenMLE post-training used a 32,768-token SFT cutoff; substantially longer contexts have not yet been validated to the same standard as the reported experiments.
+
+## Training
+
+Frontis-MA1-35B uses full-parameter supervised fine-tuning followed by reinforcement learning from executable task feedback.
+
+### Supervised fine-tuning
+
+- 26,259 released execution-grounded examples: 17,245 full responses and 9,014 trajectory steps;
+- full-solution and trajectory-step supervision;
+- BF16 full-parameter training on 8 NVIDIA H200 GPUs;
+- global batch size 128;
+- learning rate `3e-5` with cosine decay and 0.1 warmup fraction;
+- three epochs;
+- Qwen-compatible thinking-loss masking.
+
+### Reinforcement learning
+
+- online generation and evaluation in isolated task sandboxes;
+- operator mixture: Draft 0.50, Improve 0.17, Debug 0.17, Crossover 0.16;
+- 16 prompts per rollout and 16 samples per prompt;
+- maximum response length 24,576 tokens;
+- GSPO with execution-grounded reward post-processing;
+- Adam optimizer with learning rate `1e-6`.
+
+See the paper and [OpenRSI code](https://github.com/rc314159-creator/OpenRSI) for the complete data-construction, training, search, and evaluation protocol.
+
+<p align="center">
+  <img src="assets/paper-figure-openmle-framework.png" width="95%" alt="Paper framework figure: OpenMLE training and inference workflow">
+</p>
+
+<p align="center"><sub>
+Paper framework figure. Frontis-MA1 learns the same four atomic operators used by OpenMLE-Evo, first from executable SFT rollouts and then from online RL execution feedback.
+</sub></p>
+
+## Benchmark results
+
+The headline results are evaluated as **model–harness systems**, rather than as standalone one-shot generations. The controlled comparison that isolates the effect of post-training holds the OpenMLE-Evo harness fixed and changes only the model from Qwen3.6-35B-A3B to Frontis-MA1-35B.
+
+### MLE-Bench Lite protocol
+
+| Item | Setting |
+| --- | --- |
+| Benchmark | Official 22-task MLE-Bench Lite split |
+| Independent runs | 3 per OpenMLE-Evo configuration, unless stated otherwise |
+| Sandbox budget | 12 hours on 0.5 NVIDIA RTX 4090 equivalent per task |
+| Equivalent compute | 6 RTX 4090 GPU-hours per task |
+| Execution | Generated programs are run and scored in isolated task sandboxes |
+| OpenMLE-Evo-Max | MLE-Bench-disjoint task-agnostic priors plus asynchronous multi-GPU search |
+| Budget comparison | OpenMLE-Evo-Max keeps the same total sandbox-compute budget |
+
+We report three aggregate metrics:
+
+- **Valid Rate** is the mean number of the 22 tasks for which a run produces a valid submission, written as `x/22`.
+- **Medal Average** is the mean fraction of tasks receiving any Kaggle medal.
+- **Human Rank** is the fraction of human leaderboard participants surpassed by the submitted solution, averaged across tasks and runs.
+
+All three metrics are higher-is-better.
+
+### Main results from the paper
+
+<p align="center">
+  <img src="assets/paper-figure-main-results.png" width="98%" alt="Paper main figure: model-harness results on MLE-Bench Lite">
+</p>
+
+<p align="center"><sub>
+Current paper main-results figure. The left panel shows all completed model–harness results on MLE-Bench Lite; the right panel compares model size with Medal Average. Orange denotes Frontis-MA1 with OpenMLE-Evo, cyan denotes other models with OpenMLE-Evo, hatching denotes OpenMLE-Evo-Max, and gray denotes general-purpose coding harnesses.
+</sub></p>
+
+### Controlled 35B comparison
+
+| Model | Harness | Valid Rate ↑ | Medal Average ↑ | Human Rank ↑ |
+| --- | --- | ---: | ---: | ---: |
+| Qwen3.6-35B-A3B | OpenMLE-Evo | 19.67/22 | 39.39% | 0.5828 |
+| **Frontis-MA1-35B** | OpenMLE-Evo | **21.67/22** | **60.61%** | **0.7647** |
+| **Frontis-MA1-35B** | OpenMLE-Evo-Max | **22.00/22** | **71.21%** | **0.8126** |
+
+| Comparison | Δ Valid Rate | Δ Medal Average | Δ Human Rank | What it measures |
+| --- | ---: | ---: | ---: | --- |
+| Frontis-MA1-35B vs. Qwen3.6-35B-A3B, both with OpenMLE-Evo | +2.00 tasks | +21.22 pp | +0.1819 | Post-training gain under a fixed harness |
+| OpenMLE-Evo-Max vs. OpenMLE-Evo, both with Frontis-MA1-35B | +0.33 task | +10.60 pp | +0.0479 | Additional system-level search gain |
+
+The first comparison above is the primary evidence for the model improvement: the base and post-trained checkpoints are evaluated under the same standard OpenMLE-Evo harness. The second comparison holds the model fixed but changes the search system, so it should not be interpreted as a pure model gain.
+
+### Public-weight model comparison under OpenMLE-Evo
+
+The following rows use the same OpenMLE-Evo harness, benchmark split, and sandbox-compute budget. This is the closest available comparison with strong public-weight models, although model scale, pretraining data, and architecture still differ.
+
+| Public-weight model | Valid Rate ↑ | Medal Average ↑ | Human Rank ↑ |
+| --- | ---: | ---: | ---: |
+| [Kimi K2.6](https://huggingface.co/moonshotai/Kimi-K2.6) | 21.67/22 | **66.67%** | 0.7859 |
+| [GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) | 19.67/22 | 62.12% | 0.7069 |
+| **Frontis-MA1-35B** | 21.67/22 | 60.61% | 0.7647 |
+| [MiniMax M3](https://huggingface.co/MiniMaxAI/MiniMax-M3) | **22.00/22** | 59.09% | **0.7994** |
+| [Frontis-MA1-30B](https://huggingface.co/FrontisAI/Frontis-MA1-30B) | 21.67/22 | 53.03% | 0.7055 |
+| [DeepSeek-V4-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash) | 21.33/22 | 51.52% | 0.6957 |
+| [Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) | 19.67/22 | 39.39% | 0.5828 |
+| [Qwen3-30B-A3B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507) | 17.33/22 | 34.85% | 0.5573 |
+
+These are model–harness results rather than standalone one-shot model scores. The full paper figure above additionally includes OpenMLE-Evo-Max and general-purpose coding-agent systems, whose harnesses are not directly interchangeable with this fixed-harness table.
+
+### Transfer to NatureBench Lite
+
+We additionally evaluate transfer beyond competition-style MLE on a fixed 10-task NatureBench Lite subset. The subset spans all six NatureBench scientific domains, six represented input-modality families, and four ML task types. The evaluation retains the original task containers, hidden evaluator, validity rules, web-search-disabled setting, and a four-hour search budget per task.
+
+NatureBench direction-normalizes each task's metric relative to the published result. We report:
+
+- **Match-SOTA (All M):** the fraction of tasks with normalized gap `g ≥ 0`;
+- **Surpass-SOTA (All S):** the fraction of tasks with `g > 0.1`.
+
+| Model | Harness | Surpass-SOTA ↑ | Match-SOTA ↑ |
+| --- | --- | ---: | ---: |
+| **Frontis-MA1-35B** | OpenMLE-Evo NatureBench adapter | **30.0% (3/10)** | **70.0% (7/10)** |
+| Qwen3.6-35B-A3B | OpenMLE-Evo NatureBench adapter | 20.0% (2/10) | 50.0% (5/10) |
+| Qwen3.6-35B-A3B | Original AIRA-Evo | 10.0% (1/10) | 20.0% (2/10) |
+
+Holding the NatureBench adapter fixed, Frontis-MA1-35B improves over its base model by 10 percentage points on Surpass-SOTA and 20 points on Match-SOTA. Holding the base model fixed, the adapted OpenMLE-Evo harness improves over original AIRA-Evo by 10 and 30 points, respectively. Because this study contains only ten tasks, it is evidence of focused transfer rather than a claim of general scientific autonomy or performance on the full 90-task benchmark.
+
+### Long-horizon search behavior
+
+Two detailed MLE-Bench trajectories in the paper examine whether the system continues improving after it has already found an executable program.
+
+| Task | Validation Human Rank | Held-out Human Rank | Medal | Share of validation gain from late Improve/Crossover |
+| --- | ---: | ---: | --- | ---: |
+| `leaf-classification` | 0.7713 | 0.9455 | Bronze | 85.0% |
+| `mlsp-2013-birds` | 0.7284 | 0.8889 | Silver | 91.9% |
+
+These task-level traces support the intended use of Frontis-MA1-35B inside a long-horizon evolutionary loop: Debug establishes executable solutions, while later Improve and Crossover operations account for most of the measured validation improvement in the two analyzed cases. They are mechanism case studies, not additional aggregate benchmark scores.
+
+## Usage
+
+Qwen3.6 uses the newer `qwen3_5_moe` architecture. Install a recent Transformers build that includes this architecture; older releases such as Transformers 4.57.1 do not recognize the configuration. The upstream Qwen3.6 model currently recommends installing the latest `transformers[serving]`.
+
+### vLLM
+
+The paper's evaluated text/code path should be served in language-model-only mode:
+
+```bash
+vllm serve FrontisAI/Frontis-MA1-35B \
+  --served-model-name Frontis-MA1-35B \
+  --tensor-parallel-size 8 \
+  --max-model-len 32768 \
+  --reasoning-parser qwen3 \
+  --language-model-only
+```
+
+## Intended use
+
+Frontis-MA1-35B is intended for:
+
+- research on machine learning engineering and AutoResearch agents;
+- generation and iterative improvement of ML experiment code;
+- execution-grounded program search;
+- use with OpenMLE-Evo or compatible sandboxed harnesses.
+
+Generated code may be incorrect, insecure, destructive, or expensive to execute. Run it inside an isolated environment with explicit CPU, memory, GPU, network, filesystem, and time limits.
+
+## Limitations
+
+- OpenMLE post-training and the reported evaluations cover text/code behavior; the inherited vision encoder and MTP components were not post-trained or evaluated by this work.
+- The main evaluation centers on MLE-Bench Lite and does not establish general performance across all software-engineering or scientific-research tasks.
+- The paper results depend on an external evolutionary search harness and sandbox feedback.
+- Execution reward does not fully measure maintainability, robustness, security, or responsible data handling.
+- Context lengths beyond the post-training cutoff require additional validation.
+- Outputs may contain reasoning traces and should be handled according to downstream requirements.
+
+## Release artifacts
+
+This repository is the canonical BF16 Transformers release. The [Frontis-MA1-35B-GGUF](https://huggingface.co/FrontisAI/Frontis-MA1-35B-GGUF) repository provides the Q4_K_M local-deployment derivative and its required F16 multimodal projector.
+
+<a id="paper"></a>
+## Paper and citation
+
+**OpenMLE: Scaling Evolutionary MLE Agents toward Recursive Self-Improvement**
+
+The public preprint URL and archival BibTeX will be added when the paper record is available.
+
+## License
+
+Original Frontis-MA1 material is released under [CC BY-NC 4.0](LICENSE) for attribution-required, non-commercial use. Commercial use is not granted.
+
+The upstream Qwen Apache License 2.0 notice is preserved in [LICENSE-UPSTREAM-APACHE-2.0](LICENSE-UPSTREAM-APACHE-2.0) and [NOTICE](NOTICE).
+
+The license in this repository applies to the model weights, configuration files, and model documentation distributed here. Training and evaluation datasets and third-party software remain subject to their respective terms.
+
+## Acknowledgements
+
+We thank the Qwen team and the open-source communities behind Transformers, SLIME, Ray, Megatron-LM, SGLang, MLE-Bench, and the broader executable MLE research ecosystem.

chat_template.jinja

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

config.json

@@ -0,0 +1,119 @@
+{
+    "architectures": [
+        "Qwen3_5MoeForConditionalGeneration"
+    ],
+    "image_token_id": 248056,
+    "model_type": "qwen3_5_moe",
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": 248044,
+        "dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 2048,
+        "initializer_range": 0.02,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 32,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "model_type": "qwen3_5_moe_text",
+        "moe_intermediate_size": 512,
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 16,
+        "num_experts": 256,
+        "num_experts_per_tok": 8,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 2,
+        "output_router_logits": false,
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "rope_type": "default"
+        },
+        "router_aux_loss_coef": 0.001,
+        "shared_expert_intermediate_size": 512,
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.1",
+    "video_token_id": 248057,
+    "vision_config": {
+        "deepstack_visual_indexes": [],
+        "depth": 27,
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "in_channels": 3,
+        "initializer_range": 0.02,
+        "intermediate_size": 4304,
+        "model_type": "qwen3_5_moe",
+        "num_heads": 16,
+        "num_position_embeddings": 2304,
+        "out_hidden_size": 2048,
+        "patch_size": 16,
+        "spatial_merge_size": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"visual-question-answering"}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95
+}

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b061e3e2e2318ed5b738718880f531814626c5fc0be343b81dded3355bc118cb
+size 4879030400

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03bab6fab63ddec8233ffe067167fb4b63134e3f80f10f89c55dfff5c782b12e
+size 4861265992

model.safetensors.index.json

@@ -0,0 +1,1052 @@
+{
+  "metadata": {
+    "total_size": 71903645408
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.mlp.experts.down_proj": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.0.mlp.gate.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.mlp.experts.down_proj": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.1.mlp.gate.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.mlp.experts.down_proj": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.10.mlp.gate.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.mlp.experts.down_proj": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.11.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.mlp.experts.down_proj": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.12.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.A_log": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.mlp.experts.down_proj": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.13.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.mlp.experts.down_proj": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00004-of-00015.safetensors",
+    "model.language_model.layers.14.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.mlp.experts.down_proj": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.15.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.A_log": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.mlp.experts.down_proj": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.16.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.mlp.experts.down_proj": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00005-of-00015.safetensors",
+    "model.language_model.layers.17.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.A_log": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.norm.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.mlp.experts.down_proj": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.mlp.experts.down_proj": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.mlp.experts.down_proj": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00000-of-00015.safetensors",
+    "model.language_model.layers.2.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.A_log": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.mlp.experts.down_proj": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors",
+    "model.language_model.layers.20.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.mlp.experts.down_proj": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.21.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.A_log": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.norm.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.22.mlp.experts.down_proj": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.mlp.experts.down_proj": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors",
+    "model.language_model.layers.23.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.mlp.experts.down_proj": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.24.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.A_log": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.mlp.experts.down_proj": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.25.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.mlp.experts.down_proj": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00008-of-00015.safetensors",
+    "model.language_model.layers.26.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.mlp.experts.down_proj": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.27.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.A_log": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.norm.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.28.mlp.experts.down_proj": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.mlp.experts.down_proj": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.29.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.3.mlp.experts.down_proj": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.3.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.A_log": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.mlp.experts.down_proj": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.30.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.31.mlp.experts.down_proj": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.31.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.32.mlp.experts.down_proj": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.32.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.A_log": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.norm.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.33.mlp.experts.down_proj": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.dt_bias": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.34.mlp.experts.down_proj": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.34.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.mlp.experts.down_proj": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00011-of-00015.safetensors",
+    "model.language_model.layers.35.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.A_log": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.mlp.experts.down_proj": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.36.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.36.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.37.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.dt_bias": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.norm.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.37.mlp.experts.down_proj": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.37.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.37.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.38.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.A_log": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.norm.weight": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.mlp.experts.down_proj": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00012-of-00015.safetensors",
+    "model.language_model.layers.38.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.38.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.mlp.experts.down_proj": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.self_attn.q_norm.weight": "model-00014-of-00015.safetensors",
+    "model.language_model.layers.39.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.mlp.experts.down_proj": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.4.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.mlp.experts.down_proj": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00001-of-00015.safetensors",
+    "model.language_model.layers.5.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.mlp.experts.down_proj": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.6.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.mlp.experts.down_proj": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.7.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.mlp.experts.down_proj": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.8.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.A_log": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.dt_bias": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.norm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.mlp.experts.down_proj": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.9.mlp.gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.language_model.norm.weight": "model-00013-of-00015.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-vision-mtp.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-vision-mtp.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-vision-mtp.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-vision-mtp.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-vision-mtp.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-vision-mtp.safetensors",
+    "model.visual.merger.norm.bias": "model-vision-mtp.safetensors",
+    "model.visual.merger.norm.weight": "model-vision-mtp.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-vision-mtp.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-vision-mtp.safetensors",
+    "model.visual.pos_embed.weight": "model-vision-mtp.safetensors",
+    "mtp.fc.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.input_layernorm.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.mlp.experts.down_proj": "model-vision-mtp.safetensors",
+    "mtp.layers.0.mlp.experts.gate_up_proj": "model-vision-mtp.safetensors",
+    "mtp.layers.0.mlp.gate.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.mlp.shared_expert.down_proj.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.mlp.shared_expert.gate_proj.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.mlp.shared_expert.up_proj.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.mlp.shared_expert_gate.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.post_attention_layernorm.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.self_attn.k_norm.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.self_attn.k_proj.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.self_attn.o_proj.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.self_attn.q_norm.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.self_attn.q_proj.weight": "model-vision-mtp.safetensors",
+    "mtp.layers.0.self_attn.v_proj.weight": "model-vision-mtp.safetensors",
+    "mtp.norm.weight": "model-vision-mtp.safetensors",
+    "mtp.pre_fc_norm_embedding.weight": "model-vision-mtp.safetensors",
+    "mtp.pre_fc_norm_hidden.weight": "model-vision-mtp.safetensors"
+  }
+}

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"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
+size 12807982

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "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|>"
+    ],
+    "bos_token": null,
+    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "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,
+    "add_bos_token": false,
+    "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+    "extra_special_tokens": {
+        "audio_bos_token": "<|audio_start|>",
+        "audio_eos_token": "<|audio_end|>",
+        "audio_token": "<|audio_pad|>",
+        "image_token": "<|image_pad|>",
+        "video_token": "<|video_pad|>",
+        "vision_bos_token": "<|vision_start|>",
+        "vision_eos_token": "<|vision_end|>"
+    }
+}

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"
+}