OpenJev Flash 9B FP8 v1

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/accuracy_and_size.png filter=lfs diff=lfs merge=lfs -text

FP8_CONVERSION_RECEIPT.json

@@ -0,0 +1,21 @@
+{
+ "source": "openjev/OpenJev-Flash-9B@61c569f2d9d25f3446d4e585eb35cc532dca7d80",
+ "source_index_sha256": "941305ff9f77551e145a6cea976ef456cd5cb208cbece99f168376c752fcf96c",
+ "official_fp8_reference": "Qwen/Qwen3.8-27B-FP8@017b9c7af6b5689d5dd426a76e0bc077eb5ca20a",
+ "official_fp8_config_sha256": "74227dd615bf1ea975aa676bdf355a0379858c12f394b5365cd9dfa5fc2c70bc",
+ "note": "Qwen publishes no FP8 build of Qwen3.5-9B; the quantized-tensor set and quantization_config of the reference were mapped onto the 9B by layer type",
+ "scheme": "fp8 e4m3, dynamic activations, 128x128 weight blocks, scale_inv = absmax/448 (bf16)",
+ "quantized_tensors": 200,
+ "tensors_total": 960,
+ "worst_relative_dequant_error": {
+  "value": 0.03721373900771141,
+  "tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight"
+ },
+ "script_sha256": "fce98903a0332e3f775ee115fcaeaabac15eabaa1a0678eacac57e9467e339b5",
+ "quantizer_sha256": "06f75dacb52a879988023c66aed4c8b661b0910c576857a305edbac70711643d",
+ "selfcheck": [
+  "SELFCHECK model.language_model.layers.0.linear_attn.in_proj_qkv.weight: scale dtype torch.bfloat16 shape (80, 40) max rel err 0.00e+00, identical q bytes 0.99939",
+  "SELFCHECK model.language_model.layers.38.mlp.down_proj.weight: scale dtype torch.bfloat16 shape (40, 136) max rel err 0.00e+00, identical q bytes 0.99911"
+ ],
+ "torch": "2.14.1+cpu"
+}

LICENSE

@@ -0,0 +1,408 @@
+Attribution-NonCommercial 4.0 International
+
+=======================================================================
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and
+does not provide legal services or legal advice. Distribution of
+Creative Commons public licenses does not create a lawyer-client or
+other relationship. Creative Commons makes its licenses and related
+information available on an "as-is" basis. Creative Commons gives no
+warranties regarding its licenses, any material licensed under their
+terms and conditions, or any related information. Creative Commons
+disclaims all liability for damages resulting from their use to the
+fullest extent possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and
+conditions that creators and other rights holders may use to share
+original works of authorship and other material subject to copyright
+and certain other rights specified in the public license below. The
+following considerations are for informational purposes only, are not
+exhaustive, and do not form part of our licenses.
+
+     Considerations for licensors: Our public licenses are
+     intended for use by those authorized to give the public
+     permission to use material in ways otherwise restricted by
+     copyright and certain other rights. Our licenses are
+     irrevocable. Licensors should read and understand the terms
+     and conditions of the license they choose before applying it.
+     Licensors should also secure all rights necessary before
+     applying our licenses so that the public can reuse the
+     material as expected. Licensors should clearly mark any
+     material not subject to the license. This includes other CC-
+     licensed material, or material used under an exception or
+     limitation to copyright. More considerations for licensors:
+    wiki.creativecommons.org/Considerations_for_licensors
+
+     Considerations for the public: By using one of our public
+     licenses, a licensor grants the public permission to use the
+     licensed material under specified terms and conditions. If
+     the licensor's permission is not necessary for any reason--for
+     example, because of any applicable exception or limitation to
+     copyright--then that use is not regulated by the license. Our
+     licenses grant only permissions under copyright and certain
+     other rights that a licensor has authority to grant. Use of
+     the licensed material may still be restricted for other
+     reasons, including because others have copyright or other
+     rights in the material. A licensor may make special requests,
+     such as asking that all changes be marked or described.
+     Although not required by our licenses, you are encouraged to
+     respect those requests where reasonable. More considerations
+     for the public:
+    wiki.creativecommons.org/Considerations_for_licensees
+
+=======================================================================
+
+Creative Commons Attribution-NonCommercial 4.0 International Public
+License
+
+By exercising the Licensed Rights (defined below), You accept and agree
+to be bound by the terms and conditions of this Creative Commons
+Attribution-NonCommercial 4.0 International Public License ("Public
+License"). To the extent this Public License may be interpreted as a
+contract, You are granted the Licensed Rights in consideration of Your
+acceptance of these terms and conditions, and the Licensor grants You
+such rights in consideration of benefits the Licensor receives from
+making the Licensed Material available under these terms and
+conditions.
+
+
+Section 1 -- Definitions.
+
+  a. Adapted Material means material subject to Copyright and Similar
+     Rights that is derived from or based upon the Licensed Material
+     and in which the Licensed Material is translated, altered,
+     arranged, transformed, or otherwise modified in a manner requiring
+     permission under the Copyright and Similar Rights held by the
+     Licensor. For purposes of this Public License, where the Licensed
+     Material is a musical work, performance, or sound recording,
+     Adapted Material is always produced where the Licensed Material is
+     synched in timed relation with a moving image.
+
+  b. Adapter's License means the license You apply to Your Copyright
+     and Similar Rights in Your contributions to Adapted Material in
+     accordance with the terms and conditions of this Public License.
+
+  c. Copyright and Similar Rights means copyright and/or similar rights
+     closely related to copyright including, without limitation,
+     performance, broadcast, sound recording, and Sui Generis Database
+     Rights, without regard to how the rights are labeled or
+     categorized. For purposes of this Public License, the rights
+     specified in Section 2(b)(1)-(2) are not Copyright and Similar
+     Rights.
+  d. Effective Technological Measures means those measures that, in the
+     absence of proper authority, may not be circumvented under laws
+     fulfilling obligations under Article 11 of the WIPO Copyright
+     Treaty adopted on December 20, 1996, and/or similar international
+     agreements.
+
+  e. Exceptions and Limitations means fair use, fair dealing, and/or
+     any other exception or limitation to Copyright and Similar Rights
+     that applies to Your use of the Licensed Material.
+
+  f. Licensed Material means the artistic or literary work, database,
+     or other material to which the Licensor applied this Public
+     License.
+
+  g. Licensed Rights means the rights granted to You subject to the
+     terms and conditions of this Public License, which are limited to
+     all Copyright and Similar Rights that apply to Your use of the
+     Licensed Material and that the Licensor has authority to license.
+
+  h. Licensor means the individual(s) or entity(ies) granting rights
+     under this Public License.
+
+  i. NonCommercial means not primarily intended for or directed towards
+     commercial advantage or monetary compensation. For purposes of
+     this Public License, the exchange of the Licensed Material for
+     other material subject to Copyright and Similar Rights by digital
+     file-sharing or similar means is NonCommercial provided there is
+     no payment of monetary compensation in connection with the
+     exchange.
+
+  j. Share means to provide material to the public by any means or
+     process that requires permission under the Licensed Rights, such
+     as reproduction, public display, public performance, distribution,
+     dissemination, communication, or importation, and to make material
+     available to the public including in ways that members of the
+     public may access the material from a place and at a time
+     individually chosen by them.
+
+  k. Sui Generis Database Rights means rights other than copyright
+     resulting from Directive 96/9/EC of the European Parliament and of
+     the Council of 11 March 1996 on the legal protection of databases,
+     as amended and/or succeeded, as well as other essentially
+     equivalent rights anywhere in the world.
+
+  l. You means the individual or entity exercising the Licensed Rights
+     under this Public License. Your has a corresponding meaning.
+
+
+Section 2 -- Scope.
+
+  a. License grant.
+
+       1. Subject to the terms and conditions of this Public License,
+          the Licensor hereby grants You a worldwide, royalty-free,
+          non-sublicensable, non-exclusive, irrevocable license to
+          exercise the Licensed Rights in the Licensed Material to:
+
+            a. reproduce and Share the Licensed Material, in whole or
+               in part, for NonCommercial purposes only; and
+
+            b. produce, reproduce, and Share Adapted Material for
+               NonCommercial purposes only.
+
+       2. Exceptions and Limitations. For the avoidance of doubt, where
+          Exceptions and Limitations apply to Your use, this Public
+          License does not apply, and You do not need to comply with
+          its terms and conditions.
+
+       3. Term. The term of this Public License is specified in Section
+          6(a).
+
+       4. Media and formats; technical modifications allowed. The
+          Licensor authorizes You to exercise the Licensed Rights in
+          all media and formats whether now known or hereafter created,
+          and to make technical modifications necessary to do so. The
+          Licensor waives and/or agrees not to assert any right or
+          authority to forbid You from making technical modifications
+          necessary to exercise the Licensed Rights, including
+          technical modifications necessary to circumvent Effective
+          Technological Measures. For purposes of this Public License,
+          simply making modifications authorized by this Section 2(a)
+          (4) never produces Adapted Material.
+
+       5. Downstream recipients.
+
+            a. Offer from the Licensor -- Licensed Material. Every
+               recipient of the Licensed Material automatically
+               receives an offer from the Licensor to exercise the
+               Licensed Rights under the terms and conditions of this
+               Public License.
+
+            b. No downstream restrictions. You may not offer or impose
+               any additional or different terms or conditions on, or
+               apply any Effective Technological Measures to, the
+               Licensed Material if doing so restricts exercise of the
+               Licensed Rights by any recipient of the Licensed
+               Material.
+
+       6. No endorsement. Nothing in this Public License constitutes or
+          may be construed as permission to assert or imply that You
+          are, or that Your use of the Licensed Material is, connected
+          with, or sponsored, endorsed, or granted official status by,
+          the Licensor or others designated to receive attribution as
+          provided in Section 3(a)(1)(A)(i).
+
+  b. Other rights.
+
+       1. Moral rights, such as the right of integrity, are not
+          licensed under this Public License, nor are publicity,
+          privacy, and/or other similar personality rights; however, to
+          the extent possible, the Licensor waives and/or agrees not to
+          assert any such rights held by the Licensor to the limited
+          extent necessary to allow You to exercise the Licensed
+          Rights, but not otherwise.
+
+       2. Patent and trademark rights are not licensed under this
+          Public License.
+
+       3. To the extent possible, the Licensor waives any right to
+          collect royalties from You for the exercise of the Licensed
+          Rights, whether directly or through a collecting society
+          under any voluntary or waivable statutory or compulsory
+          licensing scheme. In all other cases the Licensor expressly
+          reserves any right to collect such royalties, including when
+          the Licensed Material is used other than for NonCommercial
+          purposes.
+
+
+Section 3 -- License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the
+following conditions.
+
+  a. Attribution.
+
+       1. If You Share the Licensed Material (including in modified
+          form), You must:
+
+            a. retain the following if it is supplied by the Licensor
+               with the Licensed Material:
+
+                 i. identification of the creator(s) of the Licensed
+                    Material and any others designated to receive
+                    attribution, in any reasonable manner requested by
+                    the Licensor (including by pseudonym if
+                    designated);
+
+                ii. a copyright notice;
+
+               iii. a notice that refers to this Public License;
+
+                iv. a notice that refers to the disclaimer of
+                    warranties;
+
+                 v. a URI or hyperlink to the Licensed Material to the
+                    extent reasonably practicable;
+
+            b. indicate if You modified the Licensed Material and
+               retain an indication of any previous modifications; and
+
+            c. indicate the Licensed Material is licensed under this
+               Public License, and include the text of, or the URI or
+               hyperlink to, this Public License.
+
+       2. You may satisfy the conditions in Section 3(a)(1) in any
+          reasonable manner based on the medium, means, and context in
+          which You Share the Licensed Material. For example, it may be
+          reasonable to satisfy the conditions by providing a URI or
+          hyperlink to a resource that includes the required
+          information.
+
+       3. If requested by the Licensor, You must remove any of the
+          information required by Section 3(a)(1)(A) to the extent
+          reasonably practicable.
+
+       4. If You Share Adapted Material You produce, the Adapter's
+          License You apply must not prevent recipients of the Adapted
+          Material from complying with this Public License.
+
+
+Section 4 -- Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that
+apply to Your use of the Licensed Material:
+
+  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
+     to extract, reuse, reproduce, and Share all or a substantial
+     portion of the contents of the database for NonCommercial purposes
+     only;
+
+  b. if You include all or a substantial portion of the database
+     contents in a database in which You have Sui Generis Database
+     Rights, then the database in which You have Sui Generis Database
+     Rights (but not its individual contents) is Adapted Material; and
+
+  c. You must comply with the conditions in Section 3(a) if You Share
+     all or a substantial portion of the contents of the database.
+
+For the avoidance of doubt, this Section 4 supplements and does not
+replace Your obligations under this Public License where the Licensed
+Rights include other Copyright and Similar Rights.
+
+
+Section 5 -- Disclaimer of Warranties and Limitation of Liability.
+
+  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
+     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
+     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
+     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
+     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
+     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
+     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
+     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
+     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
+     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
+
+  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
+     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
+     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
+     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
+     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
+     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
+     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
+     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
+     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
+
+  c. The disclaimer of warranties and limitation of liability provided
+     above shall be interpreted in a manner that, to the extent
+     possible, most closely approximates an absolute disclaimer and
+     waiver of all liability.
+
+
+Section 6 -- Term and Termination.
+
+  a. This Public License applies for the term of the Copyright and
+     Similar Rights licensed here. However, if You fail to comply with
+     this Public License, then Your rights under this Public License
+     terminate automatically.
+
+  b. Where Your right to use the Licensed Material has terminated under
+     Section 6(a), it reinstates:
+
+       1. automatically as of the date the violation is cured, provided
+          it is cured within 30 days of Your discovery of the
+          violation; or
+
+       2. upon express reinstatement by the Licensor.
+
+     For the avoidance of doubt, this Section 6(b) does not affect any
+     right the Licensor may have to seek remedies for Your violations
+     of this Public License.
+
+  c. For the avoidance of doubt, the Licensor may also offer the
+     Licensed Material under separate terms or conditions or stop
+     distributing the Licensed Material at any time; however, doing so
+     will not terminate this Public License.
+
+  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
+     License.
+
+
+Section 7 -- Other Terms and Conditions.
+
+  a. The Licensor shall not be bound by any additional or different
+     terms or conditions communicated by You unless expressly agreed.
+
+  b. Any arrangements, understandings, or agreements regarding the
+     Licensed Material not stated herein are separate from and
+     independent of the terms and conditions of this Public License.
+
+
+Section 8 -- Interpretation.
+
+  a. For the avoidance of doubt, this Public License does not, and
+     shall not be interpreted to, reduce, limit, restrict, or impose
+     conditions on any use of the Licensed Material that could lawfully
+     be made without permission under this Public License.
+
+  b. To the extent possible, if any provision of this Public License is
+     deemed unenforceable, it shall be automatically reformed to the
+     minimum extent necessary to make it enforceable. If the provision
+     cannot be reformed, it shall be severed from this Public License
+     without affecting the enforceability of the remaining terms and
+     conditions.
+
+  c. No term or condition of this Public License will be waived and no
+     failure to comply consented to unless expressly agreed to by the
+     Licensor.
+
+  d. Nothing in this Public License constitutes or may be interpreted
+     as a limitation upon, or waiver of, any privileges and immunities
+     that apply to the Licensor or You, including from the legal
+     processes of any jurisdiction or authority.
+
+=======================================================================
+
+Creative Commons is not a party to its public
+licenses. Notwithstanding, Creative Commons may elect to apply one of
+its public licenses to material it publishes and in those instances
+will be considered the “Licensor.” The text of the Creative Commons
+public licenses is dedicated to the public domain under the CC0 Public
+Domain Dedication. Except for the limited purpose of indicating that
+material is shared under a Creative Commons public license or as
+otherwise permitted by the Creative Commons policies published at
+creativecommons.org/policies, Creative Commons does not authorize the
+use of the trademark "Creative Commons" or any other trademark or logo
+of Creative Commons without its prior written consent including,
+without limitation, in connection with any unauthorized modifications
+to any of its public licenses or any other arrangements,
+understandings, or agreements concerning use of licensed material. For
+the avoidance of doubt, this paragraph does not form part of the
+public licenses.
+
+Creative Commons may be contacted at creativecommons.org.
+

LICENSE-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 +1,10 @@
+OpenJev Flash 9B, FP8
+
+OpenJev Flash 9B weights: Copyright the OpenJev project, released under CC BY-NC 4.0 (see LICENSE).
+
+These weights are a derivative of Qwen/Qwen3.5-9B, revision c202236235762e1c871ad0ccb60c8ee5ba337b9a, licensed under the Apache License, Version 2.0, and were produced by fine-tuning that base and merging the result into its weights. This repository holds an FP8 (e4m3, 128x128 weight blocks) conversion of the 16-bit weights at openjev/OpenJev-Flash-9B (tag v1).
+
+Base model licence: https://huggingface.co/Qwen/Qwen3.5-9B/blob/c202236235762e1c871ad0ccb60c8ee5ba337b9a/LICENSE
+The base licence text is included as LICENSE-APACHE-2.0.
+
+For a commercial licence, email support@loopai.com.

README.md

@@ -0,0 +1,66 @@
+---
+license: cc-by-nc-4.0
+base_model: openjev/OpenJev-Flash-9B
+tags:
+- decision-model
+- zero-shot-classification
+- classification
+- fp8
+- vllm
+language:
+- en
+---
+
+# OpenJev Flash 9B, FP8 checkpoint
+
+The FP8 checkpoint of [OpenJev Flash 9B](https://huggingface.co/openjev/OpenJev-Flash-9B): the same weights stored as FP8 (e4m3, 128×128 weight blocks, dynamic activations), 11.9 GB instead of 18.8 GB.
+
+**On par with Cloudflare's Clef-Flash and ahead of Kev-9B and Nimble 9B on JevBench.** The results, the API and the use cases are on the [main card](https://huggingface.co/openjev/OpenJev-Flash-9B).
+
+- **Drop-in for vLLM:** the main card's command and helper, pointed at this repository. The weights are already FP8, so nothing is quantized at load time.
+- **Matches the 16-bit model:** 80.0% on a fixed 1,789-question check, the same as the 16-bit weights, and 79.2% on the frozen 10,000 text questions against 79.4% for the 16-bit weights served in FP8.
+- **37% smaller download:** 11.9 GB instead of 18.8 GB.
+
+![Accuracy and download size of the FP8 checkpoint against the 16-bit model](assets/accuracy_and_size.png)
+
+## Measured
+
+One GPU, vLLM 0.29. The 10,000 questions go through the OpenJev helper with the card's calibration; the 1,789-question check reads the letter probabilities directly.
+
+| test | 16-bit weights | 16-bit, served in FP8 | this FP8 file |
+|---|---|---|---|
+| 10,000 text questions, 34 public sources | — | 79.4% | 79.2% |
+| fixed 1,789-question check | 80.0% | 79.7% | 80.0% |
+
+## Run it
+
+```bash
+pip install "vllm==0.29.0" "openai==3.26.0" "httpx==0.28.1"
+hf download openjev/OpenJev-Flash-9B helper/shim.py --local-dir openjev-flash-9b
+```
+
+Terminal 1, the model (downloads the weights on first start):
+
+```bash
+vllm serve openjev/OpenJev-Flash-9B-FP8 --host 127.0.0.1 --served-model-name qwen --port 8000 \
+  --enable-prefix-caching --max-model-len 16384 --gpu-memory-utilization 0.90 \
+  --limit-mm-per-prompt '{"image":1}' --trust-remote-code --max-num-seqs 16 \
+  --max-logprobs 64 --gdn-prefill-backend triton --quantization fp8
+```
+
+Terminal 2, the decision API in front of it:
+
+```bash
+VLLM=http://127.0.0.1:8000/v1 TOKENIZER=openjev/OpenJev-Flash-9B-FP8 \
+READOUT_T=1.07 READOUT_NOUL_T=1.074766 READOUT_NOUL_BIAS=0 \
+READOUT_TARGETED=1 READOUT_INSTR_STYLE=pyrepr SHIM_STAGGER=1 \
+python openjev-flash-9b/helper/shim.py --host 127.0.0.1 --port 3000
+```
+
+Then `POST /v1/systemone` as on the main card. `curl -s http://127.0.0.1:3000/v1/version` should show `T: 1.07`, `noul_t: 1.074766`, `noul_bias: 0`, targeted readout and `instr_style: "pyrepr"`; always pass the five `READOUT_*` settings above. `FP8_CONVERSION_RECEIPT.json` records the source checkpoint and the conversion method.
+
+## Licence
+
+Weights: CC BY-NC 4.0 for research and non-commercial use, with attribution, the same as the main repository. For a commercial licence, email [support@loopai.com](mailto:support@loopai.com). The licence texts and the base model's attribution are in `LICENSE`, `LICENSE-APACHE-2.0` and `NOTICE`.
+
+OpenJev is an independent project, not affiliated with TypeSafe; Jev is their product.

chat_template.jinja

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

config.json

@@ -0,0 +1,694 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.17.0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "axial"
+    },
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "modules_to_not_convert": [
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "visual.blocks.0.attn.proj",
+      "visual.blocks.0.attn.qkv_proj",
+      "visual.blocks.0.mlp.linear_fc1",
+      "visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "visual.blocks.1.attn.proj",
+      "visual.blocks.1.attn.qkv_proj",
+      "visual.blocks.1.mlp.linear_fc1",
+      "visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "visual.blocks.2.attn.proj",
+      "visual.blocks.2.attn.qkv_proj",
+      "visual.blocks.2.mlp.linear_fc1",
+      "visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "visual.blocks.3.attn.proj",
+      "visual.blocks.3.attn.qkv_proj",
+      "visual.blocks.3.mlp.linear_fc1",
+      "visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "visual.blocks.4.attn.proj",
+      "visual.blocks.4.attn.qkv_proj",
+      "visual.blocks.4.mlp.linear_fc1",
+      "visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "visual.blocks.5.attn.proj",
+      "visual.blocks.5.attn.qkv_proj",
+      "visual.blocks.5.mlp.linear_fc1",
+      "visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "visual.blocks.6.attn.proj",
+      "visual.blocks.6.attn.qkv_proj",
+      "visual.blocks.6.mlp.linear_fc1",
+      "visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "visual.blocks.7.attn.proj",
+      "visual.blocks.7.attn.qkv_proj",
+      "visual.blocks.7.mlp.linear_fc1",
+      "visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "visual.blocks.8.attn.proj",
+      "visual.blocks.8.attn.qkv_proj",
+      "visual.blocks.8.mlp.linear_fc1",
+      "visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "visual.blocks.9.attn.proj",
+      "visual.blocks.9.attn.qkv_proj",
+      "visual.blocks.9.mlp.linear_fc1",
+      "visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "visual.blocks.10.attn.proj",
+      "visual.blocks.10.attn.qkv_proj",
+      "visual.blocks.10.mlp.linear_fc1",
+      "visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "visual.blocks.11.attn.proj",
+      "visual.blocks.11.attn.qkv_proj",
+      "visual.blocks.11.mlp.linear_fc1",
+      "visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "visual.blocks.12.attn.proj",
+      "visual.blocks.12.attn.qkv_proj",
+      "visual.blocks.12.mlp.linear_fc1",
+      "visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "visual.blocks.13.attn.proj",
+      "visual.blocks.13.attn.qkv_proj",
+      "visual.blocks.13.mlp.linear_fc1",
+      "visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "visual.blocks.14.attn.proj",
+      "visual.blocks.14.attn.qkv_proj",
+      "visual.blocks.14.mlp.linear_fc1",
+      "visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "visual.blocks.15.attn.proj",
+      "visual.blocks.15.attn.qkv_proj",
+      "visual.blocks.15.mlp.linear_fc1",
+      "visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "visual.blocks.16.attn.proj",
+      "visual.blocks.16.attn.qkv_proj",
+      "visual.blocks.16.mlp.linear_fc1",
+      "visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "visual.blocks.17.attn.proj",
+      "visual.blocks.17.attn.qkv_proj",
+      "visual.blocks.17.mlp.linear_fc1",
+      "visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "visual.blocks.18.attn.proj",
+      "visual.blocks.18.attn.qkv_proj",
+      "visual.blocks.18.mlp.linear_fc1",
+      "visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "visual.blocks.19.attn.proj",
+      "visual.blocks.19.attn.qkv_proj",
+      "visual.blocks.19.mlp.linear_fc1",
+      "visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "visual.blocks.20.attn.proj",
+      "visual.blocks.20.attn.qkv_proj",
+      "visual.blocks.20.mlp.linear_fc1",
+      "visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "visual.blocks.21.attn.proj",
+      "visual.blocks.21.attn.qkv_proj",
+      "visual.blocks.21.mlp.linear_fc1",
+      "visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "visual.blocks.22.attn.proj",
+      "visual.blocks.22.attn.qkv_proj",
+      "visual.blocks.22.mlp.linear_fc1",
+      "visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "visual.blocks.23.attn.proj",
+      "visual.blocks.23.attn.qkv_proj",
+      "visual.blocks.23.mlp.linear_fc1",
+      "visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "visual.blocks.24.attn.proj",
+      "visual.blocks.24.attn.qkv_proj",
+      "visual.blocks.24.mlp.linear_fc1",
+      "visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "visual.blocks.25.attn.proj",
+      "visual.blocks.25.attn.qkv_proj",
+      "visual.blocks.25.mlp.linear_fc1",
+      "visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "visual.blocks.26.attn.proj",
+      "visual.blocks.26.attn.qkv_proj",
+      "visual.blocks.26.mlp.linear_fc1",
+      "visual.blocks.26.mlp.linear_fc2",
+      "model.visual.deepstack_merger_list.0.linear_fc1",
+      "model.visual.deepstack_merger_list.0.linear_fc2",
+      "model.visual.deepstack_merger_list.0.norm",
+      "visual.deepstack_merger_list.0.linear_fc1",
+      "visual.deepstack_merger_list.0.linear_fc2",
+      "visual.deepstack_merger_list.0.norm",
+      "model.visual.deepstack_merger_list.1.linear_fc1",
+      "model.visual.deepstack_merger_list.1.linear_fc2",
+      "model.visual.deepstack_merger_list.1.norm",
+      "visual.deepstack_merger_list.1.linear_fc1",
+      "visual.deepstack_merger_list.1.linear_fc2",
+      "visual.deepstack_merger_list.1.norm",
+      "model.visual.deepstack_merger_list.2.linear_fc1",
+      "model.visual.deepstack_merger_list.2.linear_fc2",
+      "model.visual.deepstack_merger_list.2.norm",
+      "visual.deepstack_merger_list.2.linear_fc1",
+      "visual.deepstack_merger_list.2.linear_fc2",
+      "visual.deepstack_merger_list.2.norm",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.visual.merger.norm",
+      "model.visual.patch_embed.proj",
+      "model.visual.pos_embed",
+      "visual.merger.linear_fc1",
+      "visual.merger.linear_fc2",
+      "visual.merger.norm",
+      "visual.patch_embed.proj",
+      "visual.pos_embed",
+      "visual",
+      "model.visual",
+      "lm_head",
+      "model.embed_tokens",
+      "mtp.layers.0.input_layernorm",
+      "mtp.layers.0.mlp.gate",
+      "mtp.layers.0.mlp.shared_expert_gate",
+      "mtp.layers.0.post_attention_layernorm",
+      "mtp.layers.0.self_attn.k_norm",
+      "mtp.layers.0.self_attn.q_norm",
+      "mtp.fc",
+      "mtp.norm",
+      "mtp.pre_fc_norm_embedding",
+      "mtp.pre_fc_norm_hidden",
+      "model.language_model.layers.0.input_layernorm",
+      "model.language_model.layers.0.linear_attn.A_log",
+      "model.language_model.layers.0.linear_attn.conv1d",
+      "model.language_model.layers.0.linear_attn.dt_bias",
+      "model.language_model.layers.0.linear_attn.in_proj_a",
+      "model.language_model.layers.0.linear_attn.in_proj_b",
+      "model.language_model.layers.0.linear_attn.in_proj_ba",
+      "model.language_model.layers.0.linear_attn.norm",
+      "model.language_model.layers.0.mlp.gate",
+      "model.language_model.layers.0.mlp.shared_expert_gate",
+      "model.language_model.layers.0.post_attention_layernorm",
+      "model.language_model.layers.1.input_layernorm",
+      "model.language_model.layers.1.linear_attn.A_log",
+      "model.language_model.layers.1.linear_attn.conv1d",
+      "model.language_model.layers.1.linear_attn.dt_bias",
+      "model.language_model.layers.1.linear_attn.in_proj_a",
+      "model.language_model.layers.1.linear_attn.in_proj_b",
+      "model.language_model.layers.1.linear_attn.in_proj_ba",
+      "model.language_model.layers.1.linear_attn.norm",
+      "model.language_model.layers.1.mlp.gate",
+      "model.language_model.layers.1.mlp.shared_expert_gate",
+      "model.language_model.layers.1.post_attention_layernorm",
+      "model.language_model.layers.2.input_layernorm",
+      "model.language_model.layers.2.linear_attn.A_log",
+      "model.language_model.layers.2.linear_attn.conv1d",
+      "model.language_model.layers.2.linear_attn.dt_bias",
+      "model.language_model.layers.2.linear_attn.in_proj_a",
+      "model.language_model.layers.2.linear_attn.in_proj_b",
+      "model.language_model.layers.2.linear_attn.in_proj_ba",
+      "model.language_model.layers.2.linear_attn.norm",
+      "model.language_model.layers.2.mlp.gate",
+      "model.language_model.layers.2.mlp.shared_expert_gate",
+      "model.language_model.layers.2.post_attention_layernorm",
+      "model.language_model.layers.3.input_layernorm",
+      "model.language_model.layers.3.mlp.gate",
+      "model.language_model.layers.3.mlp.shared_expert_gate",
+      "model.language_model.layers.3.post_attention_layernorm",
+      "model.language_model.layers.3.self_attn.k_norm",
+      "model.language_model.layers.3.self_attn.q_norm",
+      "model.language_model.layers.4.input_layernorm",
+      "model.language_model.layers.4.linear_attn.A_log",
+      "model.language_model.layers.4.linear_attn.conv1d",
+      "model.language_model.layers.4.linear_attn.dt_bias",
+      "model.language_model.layers.4.linear_attn.in_proj_a",
+      "model.language_model.layers.4.linear_attn.in_proj_b",
+      "model.language_model.layers.4.linear_attn.in_proj_ba",
+      "model.language_model.layers.4.linear_attn.norm",
+      "model.language_model.layers.4.mlp.gate",
+      "model.language_model.layers.4.mlp.shared_expert_gate",
+      "model.language_model.layers.4.post_attention_layernorm",
+      "model.language_model.layers.5.input_layernorm",
+      "model.language_model.layers.5.linear_attn.A_log",
+      "model.language_model.layers.5.linear_attn.conv1d",
+      "model.language_model.layers.5.linear_attn.dt_bias",
+      "model.language_model.layers.5.linear_attn.in_proj_a",
+      "model.language_model.layers.5.linear_attn.in_proj_b",
+      "model.language_model.layers.5.linear_attn.in_proj_ba",
+      "model.language_model.layers.5.linear_attn.norm",
+      "model.language_model.layers.5.mlp.gate",
+      "model.language_model.layers.5.mlp.shared_expert_gate",
+      "model.language_model.layers.5.post_attention_layernorm",
+      "model.language_model.layers.6.input_layernorm",
+      "model.language_model.layers.6.linear_attn.A_log",
+      "model.language_model.layers.6.linear_attn.conv1d",
+      "model.language_model.layers.6.linear_attn.dt_bias",
+      "model.language_model.layers.6.linear_attn.in_proj_a",
+      "model.language_model.layers.6.linear_attn.in_proj_b",
+      "model.language_model.layers.6.linear_attn.in_proj_ba",
+      "model.language_model.layers.6.linear_attn.norm",
+      "model.language_model.layers.6.mlp.gate",
+      "model.language_model.layers.6.mlp.shared_expert_gate",
+      "model.language_model.layers.6.post_attention_layernorm",
+      "model.language_model.layers.7.input_layernorm",
+      "model.language_model.layers.7.mlp.gate",
+      "model.language_model.layers.7.mlp.shared_expert_gate",
+      "model.language_model.layers.7.post_attention_layernorm",
+      "model.language_model.layers.7.self_attn.k_norm",
+      "model.language_model.layers.7.self_attn.q_norm",
+      "model.language_model.layers.8.input_layernorm",
+      "model.language_model.layers.8.linear_attn.A_log",
+      "model.language_model.layers.8.linear_attn.conv1d",
+      "model.language_model.layers.8.linear_attn.dt_bias",
+      "model.language_model.layers.8.linear_attn.in_proj_a",
+      "model.language_model.layers.8.linear_attn.in_proj_b",
+      "model.language_model.layers.8.linear_attn.in_proj_ba",
+      "model.language_model.layers.8.linear_attn.norm",
+      "model.language_model.layers.8.mlp.gate",
+      "model.language_model.layers.8.mlp.shared_expert_gate",
+      "model.language_model.layers.8.post_attention_layernorm",
+      "model.language_model.layers.9.input_layernorm",
+      "model.language_model.layers.9.linear_attn.A_log",
+      "model.language_model.layers.9.linear_attn.conv1d",
+      "model.language_model.layers.9.linear_attn.dt_bias",
+      "model.language_model.layers.9.linear_attn.in_proj_a",
+      "model.language_model.layers.9.linear_attn.in_proj_b",
+      "model.language_model.layers.9.linear_attn.in_proj_ba",
+      "model.language_model.layers.9.linear_attn.norm",
+      "model.language_model.layers.9.mlp.gate",
+      "model.language_model.layers.9.mlp.shared_expert_gate",
+      "model.language_model.layers.9.post_attention_layernorm",
+      "model.language_model.layers.10.input_layernorm",
+      "model.language_model.layers.10.linear_attn.A_log",
+      "model.language_model.layers.10.linear_attn.conv1d",
+      "model.language_model.layers.10.linear_attn.dt_bias",
+      "model.language_model.layers.10.linear_attn.in_proj_a",
+      "model.language_model.layers.10.linear_attn.in_proj_b",
+      "model.language_model.layers.10.linear_attn.in_proj_ba",
+      "model.language_model.layers.10.linear_attn.norm",
+      "model.language_model.layers.10.mlp.gate",
+      "model.language_model.layers.10.mlp.shared_expert_gate",
+      "model.language_model.layers.10.post_attention_layernorm",
+      "model.language_model.layers.11.input_layernorm",
+      "model.language_model.layers.11.mlp.gate",
+      "model.language_model.layers.11.mlp.shared_expert_gate",
+      "model.language_model.layers.11.post_attention_layernorm",
+      "model.language_model.layers.11.self_attn.k_norm",
+      "model.language_model.layers.11.self_attn.q_norm",
+      "model.language_model.layers.12.input_layernorm",
+      "model.language_model.layers.12.linear_attn.A_log",
+      "model.language_model.layers.12.linear_attn.conv1d",
+      "model.language_model.layers.12.linear_attn.dt_bias",
+      "model.language_model.layers.12.linear_attn.in_proj_a",
+      "model.language_model.layers.12.linear_attn.in_proj_b",
+      "model.language_model.layers.12.linear_attn.in_proj_ba",
+      "model.language_model.layers.12.linear_attn.norm",
+      "model.language_model.layers.12.mlp.gate",
+      "model.language_model.layers.12.mlp.shared_expert_gate",
+      "model.language_model.layers.12.post_attention_layernorm",
+      "model.language_model.layers.13.input_layernorm",
+      "model.language_model.layers.13.linear_attn.A_log",
+      "model.language_model.layers.13.linear_attn.conv1d",
+      "model.language_model.layers.13.linear_attn.dt_bias",
+      "model.language_model.layers.13.linear_attn.in_proj_a",
+      "model.language_model.layers.13.linear_attn.in_proj_b",
+      "model.language_model.layers.13.linear_attn.in_proj_ba",
+      "model.language_model.layers.13.linear_attn.norm",
+      "model.language_model.layers.13.mlp.gate",
+      "model.language_model.layers.13.mlp.shared_expert_gate",
+      "model.language_model.layers.13.post_attention_layernorm",
+      "model.language_model.layers.14.input_layernorm",
+      "model.language_model.layers.14.linear_attn.A_log",
+      "model.language_model.layers.14.linear_attn.conv1d",
+      "model.language_model.layers.14.linear_attn.dt_bias",
+      "model.language_model.layers.14.linear_attn.in_proj_a",
+      "model.language_model.layers.14.linear_attn.in_proj_b",
+      "model.language_model.layers.14.linear_attn.in_proj_ba",
+      "model.language_model.layers.14.linear_attn.norm",
+      "model.language_model.layers.14.mlp.gate",
+      "model.language_model.layers.14.mlp.shared_expert_gate",
+      "model.language_model.layers.14.post_attention_layernorm",
+      "model.language_model.layers.15.input_layernorm",
+      "model.language_model.layers.15.mlp.gate",
+      "model.language_model.layers.15.mlp.shared_expert_gate",
+      "model.language_model.layers.15.post_attention_layernorm",
+      "model.language_model.layers.15.self_attn.k_norm",
+      "model.language_model.layers.15.self_attn.q_norm",
+      "model.language_model.layers.16.input_layernorm",
+      "model.language_model.layers.16.linear_attn.A_log",
+      "model.language_model.layers.16.linear_attn.conv1d",
+      "model.language_model.layers.16.linear_attn.dt_bias",
+      "model.language_model.layers.16.linear_attn.in_proj_a",
+      "model.language_model.layers.16.linear_attn.in_proj_b",
+      "model.language_model.layers.16.linear_attn.in_proj_ba",
+      "model.language_model.layers.16.linear_attn.norm",
+      "model.language_model.layers.16.mlp.gate",
+      "model.language_model.layers.16.mlp.shared_expert_gate",
+      "model.language_model.layers.16.post_attention_layernorm",
+      "model.language_model.layers.17.input_layernorm",
+      "model.language_model.layers.17.linear_attn.A_log",
+      "model.language_model.layers.17.linear_attn.conv1d",
+      "model.language_model.layers.17.linear_attn.dt_bias",
+      "model.language_model.layers.17.linear_attn.in_proj_a",
+      "model.language_model.layers.17.linear_attn.in_proj_b",
+      "model.language_model.layers.17.linear_attn.in_proj_ba",
+      "model.language_model.layers.17.linear_attn.norm",
+      "model.language_model.layers.17.mlp.gate",
+      "model.language_model.layers.17.mlp.shared_expert_gate",
+      "model.language_model.layers.17.post_attention_layernorm",
+      "model.language_model.layers.18.input_layernorm",
+      "model.language_model.layers.18.linear_attn.A_log",
+      "model.language_model.layers.18.linear_attn.conv1d",
+      "model.language_model.layers.18.linear_attn.dt_bias",
+      "model.language_model.layers.18.linear_attn.in_proj_a",
+      "model.language_model.layers.18.linear_attn.in_proj_b",
+      "model.language_model.layers.18.linear_attn.in_proj_ba",
+      "model.language_model.layers.18.linear_attn.norm",
+      "model.language_model.layers.18.mlp.gate",
+      "model.language_model.layers.18.mlp.shared_expert_gate",
+      "model.language_model.layers.18.post_attention_layernorm",
+      "model.language_model.layers.19.input_layernorm",
+      "model.language_model.layers.19.mlp.gate",
+      "model.language_model.layers.19.mlp.shared_expert_gate",
+      "model.language_model.layers.19.post_attention_layernorm",
+      "model.language_model.layers.19.self_attn.k_norm",
+      "model.language_model.layers.19.self_attn.q_norm",
+      "model.language_model.layers.20.input_layernorm",
+      "model.language_model.layers.20.linear_attn.A_log",
+      "model.language_model.layers.20.linear_attn.conv1d",
+      "model.language_model.layers.20.linear_attn.dt_bias",
+      "model.language_model.layers.20.linear_attn.in_proj_a",
+      "model.language_model.layers.20.linear_attn.in_proj_b",
+      "model.language_model.layers.20.linear_attn.in_proj_ba",
+      "model.language_model.layers.20.linear_attn.norm",
+      "model.language_model.layers.20.mlp.gate",
+      "model.language_model.layers.20.mlp.shared_expert_gate",
+      "model.language_model.layers.20.post_attention_layernorm",
+      "model.language_model.layers.21.input_layernorm",
+      "model.language_model.layers.21.linear_attn.A_log",
+      "model.language_model.layers.21.linear_attn.conv1d",
+      "model.language_model.layers.21.linear_attn.dt_bias",
+      "model.language_model.layers.21.linear_attn.in_proj_a",
+      "model.language_model.layers.21.linear_attn.in_proj_b",
+      "model.language_model.layers.21.linear_attn.in_proj_ba",
+      "model.language_model.layers.21.linear_attn.norm",
+      "model.language_model.layers.21.mlp.gate",
+      "model.language_model.layers.21.mlp.shared_expert_gate",
+      "model.language_model.layers.21.post_attention_layernorm",
+      "model.language_model.layers.22.input_layernorm",
+      "model.language_model.layers.22.linear_attn.A_log",
+      "model.language_model.layers.22.linear_attn.conv1d",
+      "model.language_model.layers.22.linear_attn.dt_bias",
+      "model.language_model.layers.22.linear_attn.in_proj_a",
+      "model.language_model.layers.22.linear_attn.in_proj_b",
+      "model.language_model.layers.22.linear_attn.in_proj_ba",
+      "model.language_model.layers.22.linear_attn.norm",
+      "model.language_model.layers.22.mlp.gate",
+      "model.language_model.layers.22.mlp.shared_expert_gate",
+      "model.language_model.layers.22.post_attention_layernorm",
+      "model.language_model.layers.23.input_layernorm",
+      "model.language_model.layers.23.mlp.gate",
+      "model.language_model.layers.23.mlp.shared_expert_gate",
+      "model.language_model.layers.23.post_attention_layernorm",
+      "model.language_model.layers.23.self_attn.k_norm",
+      "model.language_model.layers.23.self_attn.q_norm",
+      "model.language_model.layers.24.input_layernorm",
+      "model.language_model.layers.24.linear_attn.A_log",
+      "model.language_model.layers.24.linear_attn.conv1d",
+      "model.language_model.layers.24.linear_attn.dt_bias",
+      "model.language_model.layers.24.linear_attn.in_proj_a",
+      "model.language_model.layers.24.linear_attn.in_proj_b",
+      "model.language_model.layers.24.linear_attn.in_proj_ba",
+      "model.language_model.layers.24.linear_attn.norm",
+      "model.language_model.layers.24.mlp.gate",
+      "model.language_model.layers.24.mlp.shared_expert_gate",
+      "model.language_model.layers.24.post_attention_layernorm",
+      "model.language_model.layers.25.input_layernorm",
+      "model.language_model.layers.25.linear_attn.A_log",
+      "model.language_model.layers.25.linear_attn.conv1d",
+      "model.language_model.layers.25.linear_attn.dt_bias",
+      "model.language_model.layers.25.linear_attn.in_proj_a",
+      "model.language_model.layers.25.linear_attn.in_proj_b",
+      "model.language_model.layers.25.linear_attn.in_proj_ba",
+      "model.language_model.layers.25.linear_attn.norm",
+      "model.language_model.layers.25.mlp.gate",
+      "model.language_model.layers.25.mlp.shared_expert_gate",
+      "model.language_model.layers.25.post_attention_layernorm",
+      "model.language_model.layers.26.input_layernorm",
+      "model.language_model.layers.26.linear_attn.A_log",
+      "model.language_model.layers.26.linear_attn.conv1d",
+      "model.language_model.layers.26.linear_attn.dt_bias",
+      "model.language_model.layers.26.linear_attn.in_proj_a",
+      "model.language_model.layers.26.linear_attn.in_proj_b",
+      "model.language_model.layers.26.linear_attn.in_proj_ba",
+      "model.language_model.layers.26.linear_attn.norm",
+      "model.language_model.layers.26.mlp.gate",
+      "model.language_model.layers.26.mlp.shared_expert_gate",
+      "model.language_model.layers.26.post_attention_layernorm",
+      "model.language_model.layers.27.input_layernorm",
+      "model.language_model.layers.27.mlp.gate",
+      "model.language_model.layers.27.mlp.shared_expert_gate",
+      "model.language_model.layers.27.post_attention_layernorm",
+      "model.language_model.layers.27.self_attn.k_norm",
+      "model.language_model.layers.27.self_attn.q_norm",
+      "model.language_model.layers.28.input_layernorm",
+      "model.language_model.layers.28.linear_attn.A_log",
+      "model.language_model.layers.28.linear_attn.conv1d",
+      "model.language_model.layers.28.linear_attn.dt_bias",
+      "model.language_model.layers.28.linear_attn.in_proj_a",
+      "model.language_model.layers.28.linear_attn.in_proj_b",
+      "model.language_model.layers.28.linear_attn.in_proj_ba",
+      "model.language_model.layers.28.linear_attn.norm",
+      "model.language_model.layers.28.mlp.gate",
+      "model.language_model.layers.28.mlp.shared_expert_gate",
+      "model.language_model.layers.28.post_attention_layernorm",
+      "model.language_model.layers.29.input_layernorm",
+      "model.language_model.layers.29.linear_attn.A_log",
+      "model.language_model.layers.29.linear_attn.conv1d",
+      "model.language_model.layers.29.linear_attn.dt_bias",
+      "model.language_model.layers.29.linear_attn.in_proj_a",
+      "model.language_model.layers.29.linear_attn.in_proj_b",
+      "model.language_model.layers.29.linear_attn.in_proj_ba",
+      "model.language_model.layers.29.linear_attn.norm",
+      "model.language_model.layers.29.mlp.gate",
+      "model.language_model.layers.29.mlp.shared_expert_gate",
+      "model.language_model.layers.29.post_attention_layernorm",
+      "model.language_model.layers.30.input_layernorm",
+      "model.language_model.layers.30.linear_attn.A_log",
+      "model.language_model.layers.30.linear_attn.conv1d",
+      "model.language_model.layers.30.linear_attn.dt_bias",
+      "model.language_model.layers.30.linear_attn.in_proj_a",
+      "model.language_model.layers.30.linear_attn.in_proj_b",
+      "model.language_model.layers.30.linear_attn.in_proj_ba",
+      "model.language_model.layers.30.linear_attn.norm",
+      "model.language_model.layers.30.mlp.gate",
+      "model.language_model.layers.30.mlp.shared_expert_gate",
+      "model.language_model.layers.30.post_attention_layernorm",
+      "model.language_model.layers.31.input_layernorm",
+      "model.language_model.layers.31.mlp.gate",
+      "model.language_model.layers.31.mlp.shared_expert_gate",
+      "model.language_model.layers.31.post_attention_layernorm",
+      "model.language_model.layers.31.self_attn.k_norm",
+      "model.language_model.layers.31.self_attn.q_norm"
+    ],
+    "weight_block_size": [
+      128,
+      128
+    ]
+  }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "transformers_version": "5.17.0",
+  "use_cache": true
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc9047c4a11390af67ea807733d76a434e70b1beb60a475d867897facdff8ad
+size 4506553456

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c821b2a4e4c8daee28a30bddae2fdb98aa0118c0074bcb60303375d41fe04b34
+size 2496654896

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb428291cbc3b021d0be9ae9cb7029d0e79c1674205b214896087980962632a
+size 2480482032

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b547a004ac2161860f7aad6d45c4d837818855964e5e7299815bd12c670a1b
+size 2424686632

model.safetensors.index.json

@@ -0,0 +1,965 @@
+{
+  "metadata": {},
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_z.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.out_proj.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_z.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.out_proj.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight_scale_inv": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_z.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.out_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_z.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.out_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_z.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.out_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_z.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.out_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_z.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.out_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_z.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.out_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_z.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.out_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_z.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.out_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight_scale_inv": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_z.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.out_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_z.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.out_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_z.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.out_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_z.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.out_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_z.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.out_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight_scale_inv": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_z.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.out_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight_scale_inv": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
+  }
+}

processor_config.json

@@ -0,0 +1,61 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_video_tokens": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}