Duplicate from DeepBeepMeep/LTX-2

Co-authored-by: D B M <DeepBeepMeep@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,40 @@
+*.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
+gemma-3-12b-it-qat-q4_0-unquantized/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+ltx-2.3-22b-distilled-Q4_K_M_light.gguf filter=lfs diff=lfs merge=lfs -text
+ltx-2.3-22b-distilled-Q6_K_light.gguf filter=lfs diff=lfs merge=lfs -text
+ltx-2.3-22b-distilled-Q8_0_light.gguf filter=lfs diff=lfs merge=lfs -text
+gemma4-12b-ltx-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

JoyAI-Echo_diffusion_model_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fcbfcd6dae67e42f3489a82ffbbf642b6fa616e070c29a209658a0fd5e022a
+size 37978316832

JoyAI-Echo_diffusion_model_quanto_bf16_int8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31106fd315dd3a254683ad1246c92aad0f6c5e8e656679f5ca54810efa380225
+size 19438201145

LICENSE-LTX-2.5.txt

@@ -0,0 +1,580 @@
+                  LTX-2.x Community License Agreement                   
+                     License date: August 11, 2026                      
+
+
+   By downloading, using, accessing or distributing any portion or
+   element of LTX-2.x, you agree that you have read and accepted to be
+   bound by this Agreement.
+
+   1. Definitions
+
+      1.1 "Agreement" means the terms and conditions for this LTX-2.x
+          Community License Agreement and the exhibits, attachments, and
+          Complementary Materials, as specified in this document.
+
+      1.2 "Complementary Materials" means the accompanying
+          documentation, tutorials, examples, configuration files and
+          other materials made available by Licensor together with the
+          LTX-2.x model weights and parameters, in each case as
+          distributed by Licensor.
+
+      1.3 "Control" means the direct or indirect ownership of more than
+          fifty percent (50%) of the voting securities or other
+          ownership interests, or the power to direct the management and
+          policies of such Entity through voting rights, contract, or
+          otherwise.
+
+      1.4 "Data" means a collection of information and/or content
+          extracted from the dataset used with LTX-2.x, including to
+          train, pretrain, or otherwise evaluate LTX-2.x. The Data is
+          not licensed under this Agreement.
+
+      1.5 "Derivatives of LTX-2.x" means all modifications to LTX-2.x,
+          works based on LTX-2.x, or any other model which is created or
+          initialized by transfer of patterns of the weights,
+          parameters, activations or output of LTX-2.x, to the other
+          model, in order to cause the other model to perform similarly
+          to LTX-2.x, including - but not limited to - distillation
+          methods entailing the use of intermediate data representations
+          or methods based on the generation of synthetic data by
+          LTX-2.x for training the other model. For clarity, Derivatives
+          of LTX-2.x include: (i) any fine-tuned or adapted weights,
+          parameters, or checkpoints derived from LTX-2.x; (ii)
+          derivative model architectures that incorporate or are based
+          upon LTX-2.x's architecture; and (iii) any modified or
+          extended versions of the Complementary Materials.
+
+      1.6 "Entity" means any individual, corporation, partnership,
+          limited liability company, or other legal entity. For purposes
+          of this Agreement, an Entity shall be deemed to include, on an
+          aggregative basis, all subsidiaries, affiliates, and other
+          companies under common Control with such Entity. When
+          determining whether an Entity meets any threshold under this
+          Agreement (including revenue thresholds in Section 2.1), all
+          subsidiaries, affiliates, and companies under common Control
+          shall be considered collectively.
+
+      1.7 "Harm" includes but is not limited to physical, mental,
+          psychological, financial and reputational damage, pain, or
+          loss.
+
+      1.8 "Licensor" or "LTX" means the owner that is granting the
+          license under this Agreement. For the purposes of this
+          Agreement, the Licensor is Lightricks Ltd.
+
+      1.9 "LTX-2.x" means the large generative models,
+          text/image/video/audio/3D generation models, and multimodal
+          large language models and their software and algorithms,
+          including trained model weights, parameters (including
+          optimizer states), machine-learning model code,
+          inference-enabling code, training-enabling code, fine-tuning
+          enabling code, accompanying source code, scripts, and all
+          other elements of the foregoing distributed and made publicly
+          available by LTX (including, for example, at
+          https://github.com/Lightricks/LTX-2). This license is
+          applicable to all LTX-2.5 versions released since August 11,
+          2026, and all future releases of LTX-2.x under this license.
+
+      1.10 "Output" means the results of operating LTX-2.x as embodied
+           in informational content resulting therefrom.
+
+      1.11 "you" (or "your") means an individual or legal Entity
+           licensing LTX-2.x in accordance with this Agreement and/or
+           otherwise downloading, accessing, distributing or using
+           LTX-2.x for whichever purpose and in any field of use,
+           including usage of LTX-2.x in an end-use application - e.g.
+           chatbot, translator, image generator.
+
+   2. Grant of License.
+
+      2.1 Subject to your compliance with the terms and conditions of
+          this Agreement, you are granted a non-exclusive, worldwide,
+          non-transferable and royalty-free limited license under
+          Licensor's intellectual property or other rights owned by
+          Licensor embodied in LTX-2.x to use, reproduce, prepare,
+          distribute, publicly display, publicly perform, sublicense,
+          copy, create derivative works of, and make modifications to
+          LTX-2.x, for any purpose, subject to the restrictions set
+          forth in Attachment A; provided however, that Entities with
+          annual revenues of at least $10,000,000 (the "Commercial
+          Entities") are required to obtain a paid license for any use
+          (excluding use solely for a Non-Commercial Purpose as set
+          forth in Section 2.2) of LTX-2.x and Derivatives of LTX-2.x
+          (such paid license referred to herein as a "Commercial Use
+          Agreement"), as will be provided by the Licensor. Commercial
+          Entities interested in such a commercial license are required
+          to contact Licensor (ltxv-licensing@lightricks.com). Any use
+          of LTX-2.x or Derivatives of LTX-2.x by Commercial Entities
+          not in accordance with this Agreement and/or the Commercial
+          Use Agreement is strictly prohibited and shall be deemed a
+          material breach of this Agreement. In the event of such
+          material breach, and without limiting Licensor's right to
+          terminate the Agreement or to pursue any other remedies
+          available at law or in equity, you shall pay Licensor the
+          license fees owed for the period such Commercial Entity used
+          LTX-2.x (calculated at Licensor's standard commercial license
+          fees, in effect during the relevant period or, absent
+          published standard fees, a reasonable market rate for a
+          comparable license), within thirty (30) days of Licensor's
+          written demand.
+
+      2.2 Notwithstanding the foregoing or anything to the contrary in
+          this Agreement, a Commercial Entity may download and use
+          LTX-2.x and Derivatives of LTX-2.x without obtaining the
+          Commercial Use Agreement solely for a Non-Commercial Purpose.
+          "Non-Commercial Purpose" means any of the following uses, but
+          only so far as such Commercial Entity does not receive any
+          direct or indirect payment arising from the use of LTX-2.x or
+          Derivatives of LTX-2.x: (i) use by an individual acting in a
+          personal capacity for research, experimentation, learning,
+          private study, hobby or recreational projects, or personal
+          entertainment, in each case where such use is not connected,
+          directly or indirectly, to any commercial activity, business
+          operation, or the performance of duties for an employer or any
+          other Entity; and (ii) use by a Commercial Entity for testing,
+          evaluation, or non-commercial research and development in a
+          non-production or development environment. For clarity, use
+          (a) for revenue-generating activity in any manner, whether
+          direct or indirect, (b) in direct interactions with or that
+          has impact on end users, or (c) to train, fine-tune, or
+          distill any model (including any Derivative of LTX-2.x) for
+          commercial use, in each case, is not a Non-Commercial Purpose
+          and requires all Commercial Entities to obtain a paid license
+          under the Commercial Use Agreement prior to such use. For the
+          avoidance of doubt, the permission granted under this Section
+          2.2 is a limited right of use only and does not convey or
+          transfer any ownership right, title, or interest in or to
+          LTX-2.x or any Derivatives of LTX-2.x, and all Derivatives of
+          LTX-2.x created or used pursuant to this Section 2.2 remain
+          subject to the terms of this Agreement, including Section 1.5.
+
+   3. Distribution and Redistribution. You may host for third parties
+      remote access purposes (e.g. software-as-a-service), reproduce and
+      distribute copies of LTX-2.x or Derivatives of LTX-2.x thereof in
+      any medium, with or without modifications, provided that you meet
+      the following conditions:
+
+      3.1 Use-based restrictions as referenced in Section 4 and all
+          provisions of Attachment A MUST be included as an enforceable
+          provision by you in any type of legal agreement (e.g. a
+          license) governing the use and/or distribution of LTX-2.x or
+          Derivatives of LTX-2.x, and you shall give notice to
+          subsequent users you distribute to, that LTX-2.x or
+          Derivatives of LTX-2.x are subject to Section 4 and Attachment
+          A in their entirety, including all use restrictions and
+          acceptable use policies;
+
+      3.2 You must provide any third-party recipients of LTX-2.x or
+          Derivatives of LTX-2.x a copy of this Agreement, including all
+          attachments and use policies. Any Derivative of LTX-2.x (as
+          defined in Section 1.5, including but not limited to
+          fine-tuned weights, modified training code, models trained on
+          Outputs, or any other derivative) must be distributed
+          exclusively under the terms of this Agreement, subject to
+          Section 3.6, with a complete copy of this Agreement included;
+
+      3.3 You must cause any modified files to carry prominent notices
+          stating that you changed the files;
+
+      3.4 You must retain all copyright, patent, trademark, and
+          attribution notices excluding those notices that do not
+          pertain to any part of LTX-2.x, Derivatives of LTX-2.x.
+
+      3.5 Transfer of Derivatives. No transfer of any Derivative of
+          LTX-2.x (including any fine-tuned weights, LoRA adapters, or
+          similar adaptations) to a third party shall grant such third
+          party any right, title, license, or authorization to access,
+          use, reproduce, distribute, or exploit LTX-2.x, or any
+          Derivative of LTX-2.x beyond the rights granted under this
+          Agreement. If the transferee is a Commercial Entity (as
+          defined in Section 2), it must obtain a paid license from
+          Licensor prior to any use of any Derivative of LTX-2.x,
+          regardless of who created such Derivative. Prior to or at the
+          time of any such transfer, you shall notify the transferee in
+          writing that (i) use of such Derivative of LTX-2.x is subject
+          to the terms of this Agreement, and (ii) if the transferee is
+          a Commercial Entity, it must obtain a separate paid license to
+          LTX-2.x from Licensor. You shall not transfer any Derivative
+          of LTX-2.x to a Commercial Entity unless such Commercial
+          Entity has obtained the required paid license from Licensor
+          prior to any use, and unless the proposed transferee has been
+          so informed. You and the transferee shall each be responsible
+          for ensuring the transferee obtains the required license from
+          Licensor prior to any use of LTX-2.x or Derivative of LTX-2.x.
+          Nothing in this Section 3.5 shall require a Commercial Entity
+          to obtain a paid license for use solely for a Non-Commercial
+          Purpose as permitted under Section 2.2.
+
+      3.6 You may add your own copyright statement to your modifications
+          and may provide additional license terms and conditions -
+          respecting Section 3.1 - for use, reproduction, or
+          distribution of your modifications, or for any such
+          Derivatives of LTX-2.x as a whole, provided your use,
+          reproduction, and distribution of LTX-2.x otherwise complies
+          with the conditions stated in this Agreement, and you provide
+          a complete copy of this Agreement with any such use,
+          reproduction and distribution of LTX-2.x and any Derivatives
+          thereof; provided that any such additional terms shall be
+          additive only and shall not derogate from, conflict with,
+          waive, or purport to modify any term of this Agreement, and
+          this Agreement shall govern in the event of any conflict.
+
+   4. Use-based restrictions. The restrictions set forth in Attachment A
+      are considered Use-based restrictions. Therefore, you cannot use
+      LTX-2.x and the Derivatives of LTX-2.x in violation of the
+      specified restricted uses. You may use LTX-2.x subject to this
+      Agreement, only for lawful purposes and in accordance with the
+      Agreement. "Use" may include creating any content with,
+      fine-tuning, updating, running, training, evaluating and/or
+      re-parametrizing LTX-2.x. You shall require all of your users who
+      use LTX-2.x or a Derivative of LTX-2.x to comply with the terms of
+      this Section 4.
+
+   5. The Output You Generate. Except as set forth herein, Licensor
+      claims no rights in the Output you generate using LTX-2.x. You are
+      accountable for input you insert into LTX-2.x, the Output you
+      generate and its subsequent uses. No use of the Output can
+      contravene any provision as stated in the Agreement.
+
+   6. Updates and Runtime Restrictions; AI Regulations. To the maximum
+      extent permitted by law, Licensor reserves the right to restrict
+      (remotely or otherwise) usage of LTX-2.x in violation of this
+      Agreement, update LTX-2.x through electronic means, or modify the
+      Output of LTX-2.x based on updates. You shall undertake reasonable
+      efforts to use the latest version of LTX-2.x. Any use of the
+      non-current version of LTX-2.x is done solely at your risk. To the
+      extent applicable to you, you shall comply with all laws and
+      regulations governing artificial intelligence that apply to your
+      use, deployment, or distribution of LTX-2.x, Derivatives of
+      LTX-2.x, or Outputs, including Regulation (EU) 2024/1689 (the "EU
+      AI Act") and the California AI Transparency Act (Cal. Bus. & Prof.
+      Code § 22757 et seq.), each as amended from time to time and any
+      other applicable laws, regulations, or binding guidance relating
+      to artificial intelligence, transparency, content provenance, or
+      synthetic media, together with any documentation made available by
+      Licensor regarding compliance with the same (collectively, "AI
+      Regulations"). You shall maintain (including within any
+      application or service through which LTX-2.x, any Derivative of
+      LTX-2.x, or any Output is made available), and shall not remove,
+      disable, alter, or circumvent, any safety or security measures,
+      disclosures, metadata, watermarking, content provenance, latent
+      disclosure, or other transparency features or functionalities
+      included or embedded within LTX-2.x or any Derivative of LTX-2.x,
+      or applied to any Output, in furtherance of AI Regulations,
+      including any capability of LTX-2.x to include latent disclosures
+      in Outputs, and you shall include equivalent obligations in any
+      agreement governing your distribution of LTX-2.x or any Derivative
+      of LTX-2.x. You are solely responsible for any transparency,
+      disclosure, marking, or labeling obligations applicable to you
+      under AI Regulations as a provider or deployer of LTX-2.x, any
+      Derivative of LTX-2.x, or any system incorporating any of the
+      foregoing, including any obligation to disclose that content is
+      artificially generated or manipulated. If Licensor knows or
+      reasonably believes that you have modified LTX-2.x or any
+      Derivative of LTX-2.x such that it is no longer capable of
+      including any disclosure required by AI Regulations in Outputs, or
+      that you have otherwise removed, disabled, or circumvented any
+      feature or functionality described in this Section, Licensor may
+      in its sole discretion revoke the license granted under this
+      Agreement effective immediately upon notice to you, and upon such
+      revocation you shall immediately cease all use of LTX-2.x and
+      Derivatives of LTX-2.x. Licensor makes no representation or
+      warranty that LTX-2.x, any Derivative of LTX-2.x, or any Output
+      complies with any AI Regulations applicable to your specific use
+      case or deployment, and you are solely responsible for determining
+      the applicability of, and ensuring your compliance with, all AI
+      Regulations. You shall indemnify, defend, and hold harmless
+      Licensor and its affiliates from and against any and all claims,
+      liabilities, losses, damages, costs, and expenses (including
+      reasonable attorneys' fees) arising out of or relating to your
+      use, deployment, distribution, or modification of LTX-2.x, any
+      Derivative of LTX-2.x, or any Output in violation of, or your
+      other failure to comply with, any AI Regulations.
+
+      For purposes of the EU AI Act, Licensor makes LTX-2.x openly
+      available under this community license and intends that LTX-2.x be
+      treated as a free and open-source general purpose AI model within
+      the meaning of Article 53(2) of the EU AI Act. You acknowledge and
+      agree that (a) to the extent the free and open source derogations
+      under Article 53(2) of the EU AI Act apply, Licensor's obligations
+      under the EU AI Act with respect to LTX-2.x are limited to those
+      applicable to providers of free and open source general purpose AI
+      models (it being acknowledged that such derogations do not extend
+      to the obligations under Article 53(1)(c) and (d)), (b) you
+      acknowledge that LTX-2.x is not intended to be integrated into a
+      high risk AI system, and shall be fully and solely responsible for
+      any obligation resulting from such integration, (c) if you
+      integrate LTX-2.x or any Derivative of LTX-2.x into a high-risk AI
+      system you shall be solely responsible for all provider
+      obligations that would otherwise apply to Licensor under the EU AI
+      Act, and (d) you shall not take any action, or omit to take any
+      action, that would cause Licensor to lose the benefit of the free
+      and open source derogations under the EU AI Act, and you shall
+      indemnify and hold Licensor harmless from any liability, costs, or
+      expenses arising from your breach of this Section.
+
+   7. Export Controls and Sanctions Compliance. You acknowledge that
+      LTX-2.x, Derivatives of LTX-2.x may be subject to export control
+      laws and regulations, including but not limited to the U.S. Export
+      Administration Regulations and sanctions programs administered by
+      the Office of Foreign Assets Control (OFAC). You represent and
+      warrant that you and any users of LTX-2.x are not (i) located in,
+      organized under the laws of, or ordinarily resident in any country
+      or territory subject to comprehensive sanctions; (ii) identified
+      on any U.S. government restricted party list, including the
+      Specially Designated Nationals and Blocked Persons List; or (iii)
+      otherwise prohibited from receiving LTX-2.x under applicable law.
+      You shall not export, re-export, or transfer LTX-2.x, directly or
+      indirectly, in violation of any applicable export control or
+      sanctions laws or regulations. You agree to comply with all
+      applicable trade control laws and shall indemnify and hold
+      Licensor harmless from any claims arising from your failure to
+      comply with such laws.
+
+   8. Trademarks; Reservation of Rights. Nothing in this Agreement
+      permits you to make use of Licensor's trademarks, trade names,
+      logos or to otherwise suggest endorsement or misrepresent the
+      relationship between the parties; and any rights not expressly
+      granted herein are reserved by the Licensor. Except as expressly
+      set forth in this Agreement, Licensor does not grant, directly or
+      by implication, estoppel, statute or otherwise, any right or
+      license in its, or its affiliates', intellectual property rights
+      or other proprietary rights. For avoidance of doubt, all
+      intellectual property rights in Derivatives of LTX-2.x shall be
+      subject to the terms of this Agreement, and you acquire no right,
+      title, or interest in or to LTX-2.x itself, which is and remains
+      the exclusive property of Licensor. You shall not assert any
+      ownership or other right in LTX-2.x or any Derivative of LTX-2.x
+      in any manner that restricts, encumbers, or is inconsistent with
+      the rights retained by Licensor or granted to other licensees
+      under this Agreement.
+
+   9. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides LTX-2.x 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 LTX-2.x
+      and Derivatives of LTX-2.x and assume any risks associated with
+      your exercise of permissions under this Agreement.
+
+   10. Limitation of Liability. To the fullest extent permitted by
+       applicable law, 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 Licensor be liable
+       to you or any other individual or Entity for damages, including
+       any direct, indirect, special, incidental, or consequential
+       damages of any character arising as a result of this Agreement or
+       out of the use of, or inability to use LTX-2.x or any Derivative
+       of LTX-2.x (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 Licensor has
+       been advised of the possibility of such damages.
+
+   11. Accepting Warranty or Additional Liability. While redistributing
+       LTX-2.x and Derivatives of LTX-2.x, you may, provided you do not
+       violate the terms of this Agreement, choose to offer and charge a
+       fee for, acceptance of support, warranty, indemnity, or other
+       liability obligations. However, in accepting such obligations,
+       you may act only on your own behalf and on your sole
+       responsibility, not on behalf of Licensor, and only if you agree
+       to indemnify, defend, and hold Licensor harmless for any
+       liability incurred by, or claims asserted against Licensor, by
+       reason of your accepting any such warranty or additional
+       liability.
+
+   12. Governing Law. This Agreement and all relations, disputes, claims
+       and other matters arising hereunder (including non-contractual
+       disputes or claims) will be governed exclusively by, and
+       construed exclusively in accordance with, the laws of the State
+       of New York and applicable U.S. federal law. To the extent
+       permitted by law, choice of laws rules and the United Nations
+       Convention on Contracts for the International Sale of Goods will
+       not apply. The prevailing party in any claim or dispute between
+       the parties under this Agreement will be entitled to
+       reimbursement of its reasonable attorneys' fees and costs.
+
+   13. Term and Termination. This Agreement is effective upon your
+       acceptance and continues until terminated. Licensor may terminate
+       this Agreement immediately upon written notice to you if you
+       breach any provision of this Agreement, including but not limited
+       to violations of the use restrictions in Attachment A or
+       unauthorized commercial use. This Agreement also terminates
+       immediately and automatically, without notice, upon any material
+       breach of this Agreement, including any use in violation of
+       applicable AI Regulations or any unauthorized commercial use of
+       LTX-2.x or Derivatives of LTX-2.x by a Commercial Entity. Upon
+       termination: (a) all rights granted to you under this Agreement
+       will immediately cease; (b) you must immediately cease all use of
+       LTX-2.x and Derivatives of LTX-2.x; (c) you must delete or
+       destroy all copies of LTX-2.x and Derivatives of LTX-2.x in your
+       possession or control; and (d) you must notify any third parties
+       to whom you distributed LTX-2.x or Derivatives of LTX-2.x of the
+       termination. Sections 2, 3, 4, 6-16 and Attachment A shall
+       survive termination of this Agreement. Termination does not
+       relieve you of any obligations incurred prior to termination,
+       including payment obligations under Section 2 and adhering to the
+       restrictions under Section 3. In addition, if You commence a
+       lawsuit or other proceedings (including a cross-claim or
+       counterclaim in a lawsuit) against Licensor or any person or
+       entity alleging that LTX-2.x or any Output, or any portion of any
+       of the foregoing, infringe any intellectual property or other
+       right owned or licensable by you, then all licenses granted to
+       you under this Agreement shall terminate as of the date such
+       lawsuit or other proceeding is filed.
+
+   14. Disputes and Arbitration; Waiver of Jury Trial; Class Action
+       Waiver. IF YOU ARE NOT ACTING AS A CONSUMER UNDER APPLICABLE LAW,
+       YOU HEREBY WAIVE THE RIGHT TO A TRIAL BY JURY, TO PARTICIPATE IN
+       A CLASS OR REPRESENTATIVE ACTION (INCLUDING IN ARBITRATION), OR
+       TO COMBINE INDIVIDUAL PROCEEDINGS IN COURT OR IN ARBITRATION
+       WITHOUT THE CONSENT OF ALL PARTIES. All disputes arising in
+       connection with this Agreement shall be finally settled by
+       arbitration under the Rules of Arbitration of the International
+       Chamber of Commerce ("ICC Rules"), by one (1) arbitrator
+       appointed in accordance with the ICC Rules. The seat of
+       arbitration shall be New York, NY, USA, and the proceedings shall
+       be conducted in English. The arbitrator shall be empowered to
+       grant any relief that a court could grant. Judgment on the
+       arbitration award may be entered by any court having jurisdiction
+       thereof. Notwithstanding the foregoing, either party may seek
+       injunctive or other equitable relief in respect of any actual or
+       threatened breach of the license restrictions under this
+       Agreement (including Attachment A and the Acceptable Use Policy)
+       or any actual or threatened infringement, misappropriation, or
+       violation of Licensor's intellectual property rights, in the
+       state or federal courts located in the County of New York, State
+       of New York, and each party irrevocably consents to the
+       jurisdiction of, and venue in, such courts for that limited
+       purpose. The foregoing waivers do not apply to, and are not
+       enforceable against, any licensee acting as a consumer under the
+       mandatory consumer-protection laws of its jurisdiction of
+       residence (including, without limitation, the European Union, the
+       United Kingdom, and the State of California), and nothing in this
+       Agreement limits any rights under such laws that cannot be waived
+       or limited by contract. If any waiver in this Section is held
+       invalid or unenforceable as to a particular licensee or dispute,
+       such waiver shall be severed to that extent only and shall not
+       affect the validity or enforceability of the remainder of this
+       Section.
+
+   15. In the event of any exception to the application of binding
+       arbitration, all disputes, claims, and other matters arising
+       hereunder shall be brought exclusively in the state or federal
+       courts located in the County of New York, State of New York. You
+       waive all defenses of lack of personal jurisdiction and forum non
+       conveniens with respect to venue and jurisdiction in such courts,
+       and consent to their exclusive jurisdiction and venue.
+
+   16. Severability. If any provision of this Agreement is held to be
+       invalid, illegal or unenforceable, the remaining provisions shall
+       be unaffected thereby and remain valid as if such provision had
+       not been set forth herein.
+
+                      END OF TERMS AND CONDITIONS                       
+
+                              Attachment A                              
+                            Use Restrictions                            
+
+   When using the Outputs, LTX-2.x and any Derivatives thereof, you
+   agree to comply with the Acceptable Use Policy
+   (https://static.lightricks.com/legal/ltx-acceptable-use-policy.pdf)
+   which is hereby incorporated into and made part of this Agreement by
+   reference. Licensor may update it from time to time, and the version
+   in effect at the time of your use governs; continued use after an
+   update constitutes acceptance. Licensor shall post each version of
+   the Acceptable Use Policy with its effective date, and no update
+   shall apply retroactively to use occurring before that effective
+   date. In addition, you agree not to use the Outputs, LTX-2.x or its
+   Derivatives in any of the following ways:
+
+      1) In any way that violates any applicable national, federal,
+         state, local or international law or regulation;
+
+      2) For the purpose of exploiting, Harming or attempting to exploit
+         or Harm minors in any way;
+
+      3) Knowingly generate or disseminate verifiably false information
+         and/or content with the intent to deceive, defraud, or
+         otherwise unlawfully Harm others;
+
+      4) To generate or disseminate personal identifiable information
+         that can be used to Harm an individual;
+
+      5) To generate or disseminate information and/or content (e.g.
+         images, code, posts, articles), and place the information
+         and/or content in any context (e.g. bot generating tweets)
+         without expressly and intelligibly disclaiming that the
+         information and/or content is machine generated;
+
+      6) To defame others, or to engage in the unlawful harassment of
+         others;
+
+      7) To impersonate or attempt to impersonate (e.g. deepfakes)
+         others without their consent;
+
+      8) For fully automated decision making that adversely impacts an
+         individual's legal rights or otherwise creates or modifies a
+         binding, enforceable obligation;
+
+      9) For any use intended to or which has the effect of
+         discriminating against or Harming individuals or groups based
+         on online or offline social behavior or known or predicted
+         personal or personality characteristics;
+
+      10) To exploit any of the vulnerabilities of a specific group of
+          persons based on their age, social, physical or mental
+          characteristics, in order to materially distort the behavior
+          of a person pertaining to that group in a manner that causes
+          or is likely to cause that person or another person physical
+          or psychological Harm;
+
+      11) For any use intended to or which has the effect of
+          discriminating against individuals or groups based on legally
+          protected characteristics or categories;
+
+      12) To provide medical advice and medical results interpretation;
+
+      13) To generate or disseminate information for the purpose to be
+          used for administration of justice, law enforcement,
+          immigration or asylum processes, such as predicting an
+          individual will commit fraud/crime commitment (e.g. by text
+          profiling, drawing causal relationships between assertions
+          made in documents, indiscriminate and arbitrarily-targeted
+          use);
+
+      14) To generate and/or disseminate malware (including - but not
+          limited to - ransomware) or any other content to be used for
+          the purpose of harming electronic systems;
+
+      15) To engage in, promote, incite, or facilitate discrimination or
+          other unlawful or harmful conduct in the provision of
+          employment, employment benefits, credit, housing, or other
+          essential goods and services;
+
+      16) To engage in, promote, incite, or facilitate the harassment,
+          abuse, threatening, or bullying of individuals or groups of
+          individuals;
+
+      17) For military, warfare, nuclear industries or applications,
+          weapons development, or any use in connection with activities
+          that may cause death, personal injury, or severe physical or
+          environmental damage;
+
+      18) For commercial use only: To train, improve, or fine-tune any
+          other machine learning model, artificial intelligence system,
+          or competing model, except for Derivatives of LTX-2.x as
+          expressly permitted under this Agreement;
+
+      19) To circumvent, disable, or interfere with any technical
+          limitations, safety features, content filters, watermarking,
+          content provenance or latent disclosure functionalities, or
+          use restrictions implemented in LTX-2.x by Licensor;
+
+      20) To use LTX-2.x or Derivatives of LTX-2.x in any product,
+          service, or application that directly competes with Licensor's
+          commercial products or services, or is designed to replace or
+          substitute Licensor's offerings in the market, without
+          obtaining a separate commercial license from Licensor.

LTX-2.5-MANIFEST.md

@@ -0,0 +1,43 @@
+# LTX-2.5 WanGP runtime files
+
+## Main transformers (repository root)
+
+- `ltx-2.5-22b-dev_diffusion_model_bf16.safetensors`
+- `ltx-2.5-22b-dev_diffusion_model_int8_convrot.safetensors`
+- `ltx-2.5-22b-distilled_diffusion_model_bf16.safetensors`
+- `ltx-2.5-22b-distilled_diffusion_model_int8_convrot.safetensors`
+- `ltx-2.5-22b-distilled_diffusion_model_nvfp4.safetensors`
+
+## Shared/offloadable components (repository root)
+
+- `ltx-2.5-22b_video_embeddings_connector_bf16.safetensors`
+- `ltx-2.5-22b_audio_embeddings_connector_bf16.safetensors`
+- `ltx-2.5-22b_video_embeddings_connector_int8_convrot.safetensors`
+- `ltx-2.5-22b_audio_embeddings_connector_int8_convrot.safetensors`
+- `ltx-2.5-22b_video_embeddings_connector_nvfp4_bf16.safetensors`
+- `ltx-2.5-22b_audio_embeddings_connector_nvfp4_bf16.safetensors`
+- `ltx-2.5-22b_text_embedding_projection_bf16.safetensors`
+- `ltx-2.5-22b_video_vae_bf16.safetensors`
+- `ltx-2.5-22b_audio_vae_bf16.safetensors`
+- `ltx-2.5-22b_vocoder_bf16.safetensors`
+- `ltx-2.5-spatial-upscaler-x2-1.0_bf16.safetensors`
+- `ltx-2.5-temporal-upscaler-x2-1.0_bf16.safetensors`
+
+Dev and Distilled connector tensors are shared only after equality verification. The official NVFP4 transformer has different connector values, so it uses its own BF16 connector pair.
+
+## Optional LTX-2.5 LoRA
+
+- `ltx-2.5-22b-distilled-lora-450_bf16.safetensors`
+
+This upstream LTX-2.5 LoRA is retained as an optional asset but is not automatically enabled by the WanGP LTX-2.5 defaults. LTX-2.0/2.3 LoRAs and their feature workflows remain isolated from LTX-2.5.
+
+## Gemma 4 (`gemma4-12b-ltx-v1/`)
+
+- `gemma4-12b-ltx-v1_bf16.safetensors`
+- `gemma4-12b-ltx-v1_int8_convrot.safetensors`
+- `config.json`
+- `tokenizer.json`
+- `tokenizer_config.json`
+- `chat_template.jinja`
+
+These files are derivatives of the official LTX-2.5 release and are distributed under `LICENSE-LTX-2.5.txt`.

README.md

@@ -0,0 +1,25 @@
+---
+base_model:
+- Lightricks/LTX-2
+tags:
+- diffusion-single-file
+---
+
+You will find here all the LTX-2 Video models used with WanGP (https://github.com/deepbeepmeep/Wan2GP) :
+
+
+WanGP by DeepBeepMeep : The best Open Source Video Generative Models Accessible to the GPU Poor
+
+WanGP supports the Wan (and derived models), Hunyuan Video, Flux 1 & 2, Qwen, Z-Image and LTV Video models with:
+
+Low VRAM requirements (as low as 6 GB of VRAM is sufficient for certain models)
+Support for old GPUs (RTX 10XX, 20xx, ...)
+Very Fast on the latest GPUs
+Easy to use Full Web based interface
+Auto download of the required model adapted to your specific architecture
+Tools integrated to facilitate Video Generation : Mask Editor, Prompt Enhancer, Temporal and Spatial Generation
+Loras Support to customize each model
+Queuing system : make your shopping list of videos to generate and come back later
+Discord Server to get Help from Other Users and show your Best Videos: https://discord.gg/g7efUW9jGV
+
+Follow DeepBeepMeep on Twitter/X to get the Latest News: https://x.com/deepbeepmeep

bigvgan_v2_22khz_80band_256x/bigvgan_generator.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95ba25972d3de0628d99cd156e9315a9c018899bf739988959ebe3544080ced
+size 449228171

bigvgan_v2_22khz_80band_256x/config.json

@@ -0,0 +1,63 @@
+{
+    "resblock": "1",
+    "num_gpus": 0,
+    "batch_size": 32,
+    "learning_rate": 0.0001,
+    "adam_b1": 0.8,
+    "adam_b2": 0.99,
+    "lr_decay": 0.9999996,
+    "seed": 1234,
+
+    "upsample_rates": [4,4,2,2,2,2],
+    "upsample_kernel_sizes": [8,8,4,4,4,4],
+    "upsample_initial_channel": 1536,
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+
+    "use_tanh_at_final": false,
+    "use_bias_at_final": false,
+
+    "activation": "snakebeta",
+    "snake_logscale": true,
+
+    "use_cqtd_instead_of_mrd": true,
+    "cqtd_filters": 128,
+    "cqtd_max_filters": 1024,
+    "cqtd_filters_scale": 1,
+    "cqtd_dilations": [1, 2, 4],
+    "cqtd_hop_lengths": [512, 256, 256],
+    "cqtd_n_octaves": [9, 9, 9],
+    "cqtd_bins_per_octaves": [24, 36, 48],
+
+    "mpd_reshapes": [2, 3, 5, 7, 11],
+    "use_spectral_norm": false,
+    "discriminator_channel_mult": 1,
+    
+    "use_multiscale_melloss": true,
+    "lambda_melloss": 15,
+
+    "clip_grad_norm": 500,
+
+    "segment_size": 65536,
+    "num_mels": 80,
+    "num_freq": 1025,
+    "n_fft": 1024,
+    "hop_size": 256,
+    "win_size": 1024,
+
+    "sampling_rate": 22050,
+
+    "fmin": 0,
+    "fmax": null,
+    "fmax_for_loss": null,
+
+    "normalize_volume": true,
+
+    "num_workers": 4,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54321",
+        "world_size": 1
+    }
+}

bigvgan_v2_44khz_128band_512x/bigvgan_generator.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9fe7ec6bd0b44ed9d66973d5012d8181c1570b01e5c72df51973e241dccd357
+size 489041291

bigvgan_v2_44khz_128band_512x/config.json

@@ -0,0 +1,63 @@
+{
+    "resblock": "1",
+    "num_gpus": 0,
+    "batch_size": 32,
+    "learning_rate": 0.0001,
+    "adam_b1": 0.8,
+    "adam_b2": 0.99,
+    "lr_decay": 0.9999996,
+    "seed": 1234,
+
+    "upsample_rates": [8,4,2,2,2,2],
+    "upsample_kernel_sizes": [16,8,4,4,4,4],
+    "upsample_initial_channel": 1536,
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+
+    "use_tanh_at_final": false,
+    "use_bias_at_final": false,
+
+    "activation": "snakebeta",
+    "snake_logscale": true,
+
+    "use_cqtd_instead_of_mrd": true,
+    "cqtd_filters": 128,
+    "cqtd_max_filters": 1024,
+    "cqtd_filters_scale": 1,
+    "cqtd_dilations": [1, 2, 4],
+    "cqtd_hop_lengths": [512, 256, 256],
+    "cqtd_n_octaves": [9, 9, 9],
+    "cqtd_bins_per_octaves": [24, 36, 48],
+
+    "mpd_reshapes": [2, 3, 5, 7, 11],
+    "use_spectral_norm": false,
+    "discriminator_channel_mult": 1,
+
+    "use_multiscale_melloss": true,
+    "lambda_melloss": 15,
+
+    "clip_grad_norm": 500,
+
+    "segment_size": 65536,
+    "num_mels": 128,
+    "num_freq": 2049,
+    "n_fft": 2048,
+    "hop_size": 512,
+    "win_size": 2048,
+
+    "sampling_rate": 44100,
+
+    "fmin": 0,
+    "fmax": null,
+    "fmax_for_loss": null,
+
+    "normalize_volume": true,
+
+    "num_workers": 4,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54321",
+        "world_size": 1
+    }
+}

dramabox-dit-v1_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a626525d935e8c9fb0efe124334d1e4970aeda82215d2e14ca9fe904b5c25d
+size 6575225528

dramabox-dit-v1_quanto_bf16_int8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb34d0f50fe129c77bead2854ce9ad02d6d4a372a56d0d28086c87f1098feae
+size 3350531372

edit_anything_reference_v0.1_r128_ref_adaln_proj-role_embedding-ref_attn-ref_visual_proj.module.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ffdeed38c191108229ec3085386ac10174a0730427f86ef2c20dec4c6ea663
+size 450782608

edit_anything_reference_v0.1_r128_ref_adaln_proj-role_embedding-ref_attn-ref_visual_proj.standard.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2e51d9eafd6636c9e752300578447344925b05bb5254a405302d3a6f9c668d
+size 1308756368

gemma-3-12b-it-qat-q4_0-unquantized/README.md

@@ -0,0 +1,452 @@
+---
+base_model: google/gemma-3-12b-it
+license: gemma
+tags:
+- gemma3
+- gemma
+- google
+pipeline_tag: image-text-to-text
+library_name: transformers
+extra_gated_heading: Access Gemma on Hugging Face
+extra_gated_prompt: >-
+  To access Gemma on Hugging Face, you’re required to review and agree to
+  Google’s usage license. To do this, please ensure you’re logged in to Hugging
+  Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
+---
+
+# Gemma 3 model card
+
+**Model Page**: [Gemma](https://ai.google.dev/gemma/docs/core)
+
+> [!Note]
+> This repository corresponds to the 12B **instruction-tuned** version of the Gemma 3 model using Quantization Aware Training (QAT).
+>
+> **The checkpoint in this repository is unquantized, please make sure to quantize with Q4_0 with your favorite tool**
+> 
+> Thanks to QAT, the model is able to preserve similar quality as `bfloat16` while significantly reducing the memory requirements
+> to load the model.
+
+
+**Resources and Technical Documentation**:
+
+* [Gemma 3 Technical Report][g3-tech-report]
+* [Responsible Generative AI Toolkit][rai-toolkit]
+* [Gemma on Kaggle][kaggle-gemma]
+* [Gemma on Vertex Model Garden][vertex-mg-gemma3]
+
+**Terms of Use**: [Terms][terms]
+
+**Authors**: Google DeepMind
+
+## Model Information
+
+Summary description and brief definition of inputs and outputs.
+
+### Description
+
+Gemma is a family of lightweight, state-of-the-art open models from Google,
+built from the same research and technology used to create the Gemini models.
+Gemma 3 models are multimodal, handling text and image input and generating text
+output, with open weights for both pre-trained variants and instruction-tuned
+variants. Gemma 3 has a large, 128K context window, multilingual support in over
+140 languages, and is available in more sizes than previous versions. Gemma 3
+models are well-suited for a variety of text generation and image understanding
+tasks, including question answering, summarization, and reasoning. Their
+relatively small size makes it possible to deploy them in environments with
+limited resources such as laptops, desktops or your own cloud infrastructure,
+democratizing access to state of the art AI models and helping foster innovation
+for everyone.
+
+### Inputs and outputs
+
+-   **Input:**
+    -  Text string, such as a question, a prompt, or a document to be summarized
+    -  Images, normalized to 896 x 896 resolution and encoded to 256 tokens
+       each
+    -  Total input context of 128K tokens for the 4B, 12B, and 27B sizes, and
+       32K tokens for the 1B size
+
+-   **Output:**
+    -   Generated text in response to the input, such as an answer to a
+        question, analysis of image content, or a summary of a document
+    -   Total output context of 8192 tokens
+
+### Citation
+
+```none
+@article{gemma_2025,
+    title={Gemma 3},
+    url={https://goo.gle/Gemma3Report},
+    publisher={Kaggle},
+    author={Gemma Team},
+    year={2025}
+}
+```
+
+## Model Data
+
+Data used for model training and how the data was processed.
+
+### Training Dataset
+
+These models were trained on a dataset of text data that includes a wide variety
+of sources. The 27B model was trained with 14 trillion tokens, the 12B model was
+trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and
+1B with 2 trillion tokens. Here are the key components:
+
+-   Web Documents: A diverse collection of web text ensures the model is
+    exposed to a broad range of linguistic styles, topics, and vocabulary. The
+    training dataset includes content in over 140 languages.
+-   Code: Exposing the model to code helps it to learn the syntax and
+    patterns of programming languages, which improves its ability to generate
+    code and understand code-related questions.
+-   Mathematics: Training on mathematical text helps the model learn logical
+    reasoning, symbolic representation, and to address mathematical queries.
+-   Images: A wide range of images enables the model to perform image
+    analysis and visual data extraction tasks.
+
+The combination of these diverse data sources is crucial for training a powerful
+multimodal model that can handle a wide variety of different tasks and data
+formats.
+
+### Data Preprocessing
+
+Here are the key data cleaning and filtering methods applied to the training
+data:
+
+-   CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering
+    was applied at multiple stages in the data preparation process to ensure
+    the exclusion of harmful and illegal content.
+-   Sensitive Data Filtering: As part of making Gemma pre-trained models
+    safe and reliable, automated techniques were used to filter out certain
+    personal information and other sensitive data from training sets.
+-   Additional methods: Filtering based on content quality and safety in
+    line with [our policies][safety-policies].
+
+## Implementation Information
+
+Details about the model internals.
+
+### Hardware
+
+Gemma was trained using [Tensor Processing Unit (TPU)][tpu] hardware (TPUv4p,
+TPUv5p and TPUv5e). Training vision-language models (VLMS) requires significant
+computational power. TPUs, designed specifically for matrix operations common in
+machine learning, offer several advantages in this domain:
+
+-   Performance: TPUs are specifically designed to handle the massive
+    computations involved in training VLMs. They can speed up training
+    considerably compared to CPUs.
+-   Memory: TPUs often come with large amounts of high-bandwidth memory,
+    allowing for the handling of large models and batch sizes during training.
+    This can lead to better model quality.
+-   Scalability: TPU Pods (large clusters of TPUs) provide a scalable
+    solution for handling the growing complexity of large foundation models.
+    You can distribute training across multiple TPU devices for faster and more
+    efficient processing.
+-   Cost-effectiveness: In many scenarios, TPUs can provide a more
+    cost-effective solution for training large models compared to CPU-based
+    infrastructure, especially when considering the time and resources saved
+    due to faster training.
+-   These advantages are aligned with
+    [Google's commitments to operate sustainably][sustainability].
+
+### Software
+
+Training was done using [JAX][jax] and [ML Pathways][ml-pathways].
+
+JAX allows researchers to take advantage of the latest generation of hardware,
+including TPUs, for faster and more efficient training of large models. ML
+Pathways is Google's latest effort to build artificially intelligent systems
+capable of generalizing across multiple tasks. This is specially suitable for
+foundation models, including large language models like these ones.
+
+Together, JAX and ML Pathways are used as described in the
+[paper about the Gemini family of models][gemini-2-paper]; *"the 'single
+controller' programming model of Jax and Pathways allows a single Python
+process to orchestrate the entire training run, dramatically simplifying the
+development workflow."*
+
+## Evaluation
+
+> [!Note]
+> The evaluation in this section correspond to the original checkpoint, not the QAT checkpoint.
+>
+
+Model evaluation metrics and results.
+
+### Benchmark Results
+
+These models were evaluated against a large collection of different datasets and
+metrics to cover different aspects of text generation:
+
+#### Reasoning and factuality
+
+| Benchmark                      | Metric         | Gemma 3 PT 1B  | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
+| ------------------------------ |----------------|:--------------:|:-------------:|:--------------:|:--------------:|
+| [HellaSwag][hellaswag]         | 10-shot        |      62.3      |      77.2     |      84.2      |      85.6      |
+| [BoolQ][boolq]                 | 0-shot         |      63.2      |      72.3     |      78.8      |      82.4      |
+| [PIQA][piqa]                   | 0-shot         |      73.8      |      79.6     |      81.8      |      83.3      |
+| [SocialIQA][socialiqa]         | 0-shot         |      48.9      |      51.9     |      53.4      |      54.9      |
+| [TriviaQA][triviaqa]           | 5-shot         |      39.8      |      65.8     |      78.2      |      85.5      |
+| [Natural Questions][naturalq]  | 5-shot         |      9.48      |      20.0     |      31.4      |      36.1      |
+| [ARC-c][arc]                   | 25-shot        |      38.4      |      56.2     |      68.9      |      70.6      |
+| [ARC-e][arc]                   | 0-shot         |      73.0      |      82.4     |      88.3      |      89.0      |
+| [WinoGrande][winogrande]       | 5-shot         |      58.2      |      64.7     |      74.3      |      78.8      |
+| [BIG-Bench Hard][bbh]          | few-shot       |      28.4      |      50.9     |      72.6      |      77.7      |
+| [DROP][drop]                   | 1-shot         |      42.4      |      60.1     |      72.2      |      77.2      |
+
+[hellaswag]: https://arxiv.org/abs/1905.07830
+[boolq]: https://arxiv.org/abs/1905.10044
+[piqa]: https://arxiv.org/abs/1911.11641
+[socialiqa]: https://arxiv.org/abs/1904.09728
+[triviaqa]: https://arxiv.org/abs/1705.03551
+[naturalq]: https://github.com/google-research-datasets/natural-questions
+[arc]: https://arxiv.org/abs/1911.01547
+[winogrande]: https://arxiv.org/abs/1907.10641
+[bbh]: https://paperswithcode.com/dataset/bbh
+[drop]: https://arxiv.org/abs/1903.00161
+
+#### STEM and code
+
+| Benchmark                      | Metric         | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
+| ------------------------------ |----------------|:-------------:|:--------------:|:--------------:|
+| [MMLU][mmlu]                   | 5-shot         |      59.6     |      74.5      |      78.6      |
+| [MMLU][mmlu] (Pro COT)         | 5-shot         |      29.2     |      45.3      |      52.2      |
+| [AGIEval][agieval]             | 3-5-shot       |      42.1     |      57.4      |      66.2      |
+| [MATH][math]                   | 4-shot         |      24.2     |      43.3      |      50.0      |
+| [GSM8K][gsm8k]                 | 8-shot         |      38.4     |      71.0      |      82.6      |
+| [GPQA][gpqa]                   | 5-shot         |      15.0     |      25.4      |      24.3      |
+| [MBPP][mbpp]                   | 3-shot         |      46.0     |      60.4      |      65.6      |
+| [HumanEval][humaneval]         | 0-shot         |      36.0     |      45.7      |      48.8      |
+
+[mmlu]: https://arxiv.org/abs/2009.03300
+[agieval]: https://arxiv.org/abs/2304.06364
+[math]: https://arxiv.org/abs/2103.03874
+[gsm8k]: https://arxiv.org/abs/2110.14168
+[gpqa]: https://arxiv.org/abs/2311.12022
+[mbpp]: https://arxiv.org/abs/2108.07732
+[humaneval]: https://arxiv.org/abs/2107.03374
+
+#### Multilingual
+
+| Benchmark                            | Gemma 3 PT 1B | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
+| ------------------------------------ |:-------------:|:-------------:|:--------------:|:--------------:|
+| [MGSM][mgsm]                         |      2.04     |      34.7     |      64.3     |      74.3     |
+| [Global-MMLU-Lite][global-mmlu-lite] |      24.9     |      57.0     |      69.4     |      75.7     |
+| [WMT24++][wmt24pp] (ChrF)            |      36.7     |      48.4     |      53.9     |      55.7     |
+| [FloRes][flores]                     |      29.5     |      39.2     |      46.0     |      48.8     |
+| [XQuAD][xquad] (all)                 |      43.9     |      68.0     |      74.5     |      76.8     |
+| [ECLeKTic][eclektic]                 |      4.69     |      11.0     |      17.2     |      24.4     |
+| [IndicGenBench][indicgenbench]       |      41.4     |      57.2     |      61.7     |      63.4     |
+
+[mgsm]: https://arxiv.org/abs/2210.03057
+[flores]: https://arxiv.org/abs/2106.03193
+[xquad]: https://arxiv.org/abs/1910.11856v3
+[global-mmlu-lite]: https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite
+[wmt24pp]: https://arxiv.org/abs/2502.12404v1
+[eclektic]: https://arxiv.org/abs/2502.21228
+[indicgenbench]: https://arxiv.org/abs/2404.16816
+
+#### Multimodal
+
+| Benchmark                      | Gemma 3 PT 4B | Gemma 3 PT 12B | Gemma 3 PT 27B |
+| ------------------------------ |:-------------:|:--------------:|:--------------:|
+| [COCOcap][coco-cap]            |      102      |      111       |      116       |
+| [DocVQA][docvqa] (val)         |      72.8     |      82.3      |      85.6      |
+| [InfoVQA][info-vqa] (val)      |      44.1     |      54.8      |      59.4      |
+| [MMMU][mmmu] (pt)              |      39.2     |      50.3      |      56.1      |
+| [TextVQA][textvqa] (val)       |      58.9     |      66.5      |      68.6      |
+| [RealWorldQA][realworldqa]     |      45.5     |      52.2      |      53.9      |
+| [ReMI][remi]                   |      27.3     |      38.5      |      44.8      |
+| [AI2D][ai2d]                   |      63.2     |      75.2      |      79.0      |
+| [ChartQA][chartqa]             |      63.6     |      74.7      |      76.3      |
+| [VQAv2][vqav2]                 |      63.9     |      71.2      |      72.9      |
+| [BLINK][blinkvqa]              |      38.0     |      35.9      |      39.6      |
+| [OKVQA][okvqa]                 |      51.0     |      58.7      |      60.2      |
+| [TallyQA][tallyqa]             |      42.5     |      51.8      |      54.3      |
+| [SpatialSense VQA][ss-vqa]     |      50.9     |      60.0      |      59.4      |
+| [CountBenchQA][countbenchqa]   |      26.1     |      17.8      |      68.0      |
+
+[coco-cap]: https://cocodataset.org/#home
+[docvqa]: https://www.docvqa.org/
+[info-vqa]: https://arxiv.org/abs/2104.12756
+[mmmu]: https://arxiv.org/abs/2311.16502
+[textvqa]: https://textvqa.org/
+[realworldqa]: https://paperswithcode.com/dataset/realworldqa
+[remi]: https://arxiv.org/html/2406.09175v1
+[ai2d]: https://allenai.org/data/diagrams
+[chartqa]: https://arxiv.org/abs/2203.10244
+[vqav2]: https://visualqa.org/index.html
+[blinkvqa]: https://arxiv.org/abs/2404.12390
+[okvqa]: https://okvqa.allenai.org/
+[tallyqa]: https://arxiv.org/abs/1810.12440
+[ss-vqa]: https://arxiv.org/abs/1908.02660
+[countbenchqa]: https://github.com/google-research/big_vision/blob/main/big_vision/datasets/countbenchqa/
+
+## Ethics and Safety
+
+Ethics and safety evaluation approach and results.
+
+### Evaluation Approach
+
+Our evaluation methods include structured evaluations and internal red-teaming
+testing of relevant content policies. Red-teaming was conducted by a number of
+different teams, each with different goals and human evaluation metrics. These
+models were evaluated against a number of different categories relevant to
+ethics and safety, including:
+
+-   **Child Safety**: Evaluation of text-to-text and image to text prompts
+    covering child safety policies, including child sexual abuse and
+    exploitation.
+-   **Content Safety:** Evaluation of text-to-text and image to text prompts
+    covering safety policies including, harassment, violence and gore, and hate
+    speech.
+-   **Representational Harms**: Evaluation of text-to-text and image to text
+    prompts covering safety policies including bias, stereotyping, and harmful
+    associations or inaccuracies.
+
+In addition to development level evaluations, we conduct "assurance
+evaluations" which are our 'arms-length' internal evaluations for responsibility
+governance decision making. They are conducted separately from the model
+development team, to inform decision making about release. High level findings
+are fed back to the model team, but prompt sets are held-out to prevent
+overfitting and preserve the results' ability to inform decision making.
+Assurance evaluation results are reported to our Responsibility & Safety Council
+as part of release review.
+
+### Evaluation Results
+
+For all areas of safety testing, we saw major improvements in the categories of
+child safety, content safety, and representational harms relative to previous
+Gemma models. All testing was conducted without safety filters to evaluate the
+model capabilities and behaviors. For both text-to-text and image-to-text, and
+across all model sizes, the model produced minimal policy violations, and showed
+significant improvements over previous Gemma models' performance with respect
+to ungrounded inferences. A limitation of our evaluations was they included only
+English language prompts.
+
+## Usage and Limitations
+
+These models have certain limitations that users should be aware of.
+
+### Intended Usage
+
+Open vision-language models (VLMs) models have a wide range of applications
+across various industries and domains. The following list of potential uses is
+not comprehensive. The purpose of this list is to provide contextual information
+about the possible use-cases that the model creators considered as part of model
+training and development.
+
+-   Content Creation and Communication
+    -   Text Generation: These models can be used to generate creative text
+        formats such as poems, scripts, code, marketing copy, and email drafts.
+    -   Chatbots and Conversational AI: Power conversational interfaces
+        for customer service, virtual assistants, or interactive applications.
+    -   Text Summarization: Generate concise summaries of a text corpus,
+        research papers, or reports.
+    -   Image Data Extraction: These models can be used to extract,
+        interpret, and summarize visual data for text communications.
+-   Research and Education
+    -   Natural Language Processing (NLP) and VLM Research: These
+        models can serve as a foundation for researchers to experiment with VLM
+        and NLP techniques, develop algorithms, and contribute to the
+        advancement of the field.
+    -   Language Learning Tools: Support interactive language learning
+        experiences, aiding in grammar correction or providing writing practice.
+    -   Knowledge Exploration: Assist researchers in exploring large
+        bodies of text by generating summaries or answering questions about
+        specific topics.
+
+### Limitations
+
+-   Training Data
+    -   The quality and diversity of the training data significantly
+        influence the model's capabilities. Biases or gaps in the training data
+        can lead to limitations in the model's responses.
+    -   The scope of the training dataset determines the subject areas
+        the model can handle effectively.
+-   Context and Task Complexity
+    -   Models are better at tasks that can be framed with clear
+        prompts and instructions. Open-ended or highly complex tasks might be
+        challenging.
+    -   A model's performance can be influenced by the amount of context
+        provided (longer context generally leads to better outputs, up to a
+        certain point).
+-   Language Ambiguity and Nuance
+    -   Natural language is inherently complex. Models might struggle
+        to grasp subtle nuances, sarcasm, or figurative language.
+-   Factual Accuracy
+    -   Models generate responses based on information they learned
+        from their training datasets, but they are not knowledge bases. They
+        may generate incorrect or outdated factual statements.
+-   Common Sense
+    -   Models rely on statistical patterns in language. They might
+        lack the ability to apply common sense reasoning in certain situations.
+
+### Ethical Considerations and Risks
+
+The development of vision-language models (VLMs) raises several ethical
+concerns. In creating an open model, we have carefully considered the following:
+
+-   Bias and Fairness
+    -   VLMs trained on large-scale, real-world text and image data can
+        reflect socio-cultural biases embedded in the training material. These
+        models underwent careful scrutiny, input data pre-processing described
+        and posterior evaluations reported in this card.
+-   Misinformation and Misuse
+    -   VLMs can be misused to generate text that is false, misleading,
+        or harmful.
+    -   Guidelines are provided for responsible use with the model, see the
+        [Responsible Generative AI Toolkit][rai-toolkit].
+-   Transparency and Accountability:
+    -   This model card summarizes details on the models' architecture,
+        capabilities, limitations, and evaluation processes.
+    -   A responsibly developed open model offers the opportunity to
+        share innovation by making VLM technology accessible to developers and
+        researchers across the AI ecosystem.
+
+Risks identified and mitigations:
+
+-   **Perpetuation of biases**: It's encouraged to perform continuous
+    monitoring (using evaluation metrics, human review) and the exploration of
+    de-biasing techniques during model training, fine-tuning, and other use
+    cases.
+-   **Generation of harmful content**: Mechanisms and guidelines for content
+    safety are essential. Developers are encouraged to exercise caution and
+    implement appropriate content safety safeguards based on their specific
+    product policies and application use cases.
+-   **Misuse for malicious purposes**: Technical limitations and developer
+    and end-user education can help mitigate against malicious applications of
+    VLMs. Educational resources and reporting mechanisms for users to flag
+    misuse are provided. Prohibited uses of Gemma models are outlined in the
+    [Gemma Prohibited Use Policy][prohibited-use].
+-   **Privacy violations**: Models were trained on data filtered for removal
+    of certain personal information and other sensitive data. Developers are
+    encouraged to adhere to privacy regulations with privacy-preserving
+    techniques.
+
+### Benefits
+
+At the time of release, this family of models provides high-performance open
+vision-language model implementations designed from the ground up for
+responsible AI development compared to similarly sized models.
+
+Using the benchmark evaluation metrics described in this document, these models
+have shown to provide superior performance to other, comparably-sized open model
+alternatives.
+
+[g3-tech-report]: https://goo.gle/Gemma3Report
+[rai-toolkit]: https://ai.google.dev/responsible
+[kaggle-gemma]: https://www.kaggle.com/models/google/gemma-3
+[vertex-mg-gemma3]: https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemma3
+[terms]: https://ai.google.dev/gemma/terms
+[safety-policies]: https://ai.google/static/documents/ai-responsibility-update-published-february-2025.pdf
+[prohibited-use]: https://ai.google.dev/gemma/prohibited_use_policy
+[tpu]: https://cloud.google.com/tpu/docs/intro-to-tpu
+[sustainability]: https://sustainability.google/operating-sustainably/
+[jax]: https://github.com/jax-ml/jax
+[ml-pathways]: https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/
+[sustainability]: https://sustainability.google/operating-sustainably/
+[gemini-2-paper]: https://arxiv.org/abs/2312.11805

gemma-3-12b-it-qat-q4_0-unquantized/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

gemma-3-12b-it-qat-q4_0-unquantized/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
+}

gemma-3-12b-it-qat-q4_0-unquantized/config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
+}

gemma-3-12b-it-qat-q4_0-unquantized/config_light.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "cache_implementation": "hybrid",
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3840,
+  "initializer_range": 0.02,
+  "intermediate_size": 15360,
+  "max_position_embeddings": 131072,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": {
+    "factor": 8.0,
+    "rope_type": "linear"
+  },
+  "rope_theta": 1000000,
+  "sliding_window": 1024,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": true,
+  "vocab_size": 262208
+}

gemma-3-12b-it-qat-q4_0-unquantized/gemma-3-12b-it-qat-q4_0-unquantized.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073717ab1964fb2d5a7a410cecb5b76de72525bf578cc4f99432cd231d06997a
+size 24374806648

gemma-3-12b-it-qat-q4_0-unquantized/gemma-3-12b-it-qat-q4_0-unquantized_quanto_bf16_int8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fad55b5df6c660c7982985c8ced76369114b1d31bbec93fbecc66a8bf30f36a
+size 13210647730

gemma-3-12b-it-qat-q4_0-unquantized/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.52.0.dev0"
+}

gemma-3-12b-it-qat-q4_0-unquantized/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

gemma-3-12b-it-qat-q4_0-unquantized/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

gemma-3-12b-it-qat-q4_0-unquantized/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gemma-3-12b-it-qat-q4_0-unquantized/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4046bf0505a327dd5a0abbb427ecd4fc82f99c2ceaa170bc61ecde12809b0c
+size 33384570

gemma-3-12b-it-qat-q4_0-unquantized/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

gemma4-12b-ltx-v1/chat_template.jinja

@@ -0,0 +1,390 @@
+{#
+  Template: Google Gemma 4 Canonical Chat Template
+  Author: Google Gemma Engineering Team
+  Published: 2026-07-09
+  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
+#}
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if not filter_keys or key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'OBJECT' -%}
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                    }
+                {%- elif value is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is none -%}
+        {{- 'null' -}}
+    {%- elif argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+
+{#- ===== SETUP ===== -#}
+{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
+{%- set loop_messages = messages -%}
+{%- set enable_thinking = enable_thinking | default(false) -%}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
+    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+
+    {%- endif -%}
+
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
+    {%- if thinking_text and thinking_gate -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message.get('tool_calls') -%}
+                {%- for tool_call in message.get('tool_calls') -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is none -%}
+                    {%- else -%}
+                        {{- raise_exception(
+                            "chat_template: tool_calls[].function.arguments must be a "
+                            "JSON object (mapping), not a string. Deserialize arguments "
+                            "before passing to the template."
+                        ) -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message.get('tool_responses') -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
+                        {%- for tc in message.get('tool_calls') -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') in ['image', 'image_url'] -%}
+                                    {{- '<|image|>' -}}
+                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
+                                    {{- '<|audio|>' -}}
+                                {%- elif part.get('type') == 'video' -%}
+                                    {{- '<|video|>' -}}
+                                {%- endif -%}
+                            {%- endfor -%}
+                        {%- else -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- endif -%}
+                        {%- set ns_tr_out.flag = true -%}
+                        {%- set ns.prev_message_type = 'tool_response' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+            {%- set captured_content -%}
+            {%- if message.get('content') is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message.get('content') is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item.get('type') == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item.get('type') in ['image', 'image_url'] -%}
+                        {{- '<|image|>' -}}
+                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
+                        {{- '<|audio|>' -}}
+                    {%- elif item.get('type') == 'video' -%}
+                        {{- '<|video|>' -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {#- Forward-scan: find next non-tool message role for continuation detection -#}
+        {%- set next_nt = namespace(role=None, found=false) -%}
+        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
+            {%- if not next_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set next_nt.role = loop_messages[j]['role'] -%}
+                    {%- set next_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+
+        {%- set continues_into_next = (
+            role == 'model'
+            and next_nt.role == 'assistant'
+            and (not message.get('tool_calls') or ns_tr_out.flag)
+        ) -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif continues_into_next -%}
+        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+
+    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
+    {%- set ns.prev_non_tool_role = message['role'] -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+        {%- if not enable_thinking -%}
+            {{- '<|channel>thought\n<channel|>' -}}
+        {%- endif -%}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
+    {%- endif -%}
+{%- endif -%}

gemma4-12b-ltx-v1/config.json

@@ -0,0 +1,100 @@
+{
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_k_eq_v": true,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "enable_moe_block": false,
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "global_head_dim": 512,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3840,
+  "hidden_size_per_layer_input": 0,
+  "initializer_range": 0.02,
+  "intermediate_size": 15360,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "model_type": "gemma4_unified_text",
+  "moe_intermediate_size": null,
+  "num_attention_heads": 16,
+  "num_experts": null,
+  "num_global_key_value_heads": 1,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_kv_shared_layers": 0,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 1000000.0,
+      "rope_type": "proportional"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 1024,
+  "tie_word_embeddings": true,
+  "top_k_experts": null,
+  "use_bidirectional_attention": "vision",
+  "use_cache": true,
+  "use_double_wide_mlp": false,
+  "vocab_size": 262144,
+  "vocab_size_per_layer_input": 262144,
+  "architectures": [
+    "Gemma4UnifiedForCausalLM"
+  ]
+}

gemma4-12b-ltx-v1/gemma4-12b-ltx-v1_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bee560374b6556c499bf162c45c773b0dc87dba4fc84999627f2f3f92a3d872
+size 23814782152

gemma4-12b-ltx-v1/gemma4-12b-ltx-v1_int8_convrot.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a23b673266b65a318e26cad27fabd5c67609f4ecf51aa13996feb07d0060903
+size 12923893224

gemma4-12b-ltx-v1/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

gemma4-12b-ltx-v1/tokenizer_config.json

@@ -0,0 +1,142 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4UnifiedProcessor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "fields": {
+      "content": {
+        "close": [
+          "<turn|>",
+          "<|tool_response>",
+          "<eos>"
+        ],
+        "content": "text"
+      },
+      "thinking": {
+        "close": "<channel|>",
+        "content": "text",
+        "open": "<|channel>thought\n"
+      },
+      "tool_calls": {
+        "close": "<tool_call|>",
+        "content": "json",
+        "content_args": {
+          "string_delims": [
+            [
+              "<|\"|>",
+              "<|\"|>"
+            ]
+          ],
+          "unquoted_keys": true
+        },
+        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
+        "repeats": true,
+        "transform": {
+          "function": {
+            "arguments": "{content}",
+            "name": "{name}"
+          },
+          "type": "function"
+        }
+      }
+    },
+    "start_anchor": [
+      "<|turn>model\n",
+      "<tool_response|>"
+    ]
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

hubert-large-ll60k/config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "facebook/hubert-large-ll60k",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "hubert",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "transformers_version": "4.10.0.dev0",
+  "vocab_size": 32,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer"
+}

hubert-large-ll60k/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

hubert-large-ll60k/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a299050945479a68cffe2ab7a63fd08931718ba18f05a42dbb86a5164178e0
+size 1261920069

id-lora-celebvhq-ltx2.3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e6be9c52c83047cb71470c1c63b64ebc8b13dc0dfa34400f6576ba2cd88ecf
+size 1157884304

id-lora-celebvhq-ltx2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2369a6adaba1fd2c37da07d8d56a762c3d95bf14c8f19f57b3150ccfb7804d78
+size 1157884288

kokoro/config.json

@@ -0,0 +1,150 @@
+{
+  "istftnet": {
+    "upsample_kernel_sizes": [20, 12],
+    "upsample_rates": [10, 6],
+    "gen_istft_hop_size": 5,
+    "gen_istft_n_fft": 20,
+    "resblock_dilation_sizes": [
+      [1, 3, 5],
+      [1, 3, 5],
+      [1, 3, 5]
+    ],
+    "resblock_kernel_sizes": [3, 7, 11],
+    "upsample_initial_channel": 512
+  },
+  "dim_in": 64,
+  "dropout": 0.2,
+  "hidden_dim": 512,
+  "max_conv_dim": 512,
+  "max_dur": 50,
+  "multispeaker": true,
+  "n_layer": 3,
+  "n_mels": 80,
+  "n_token": 178,
+  "style_dim": 128,
+  "text_encoder_kernel_size": 5,
+  "plbert": {
+    "hidden_size": 768,
+    "num_attention_heads": 12,
+    "intermediate_size": 2048,
+    "max_position_embeddings": 512,
+    "num_hidden_layers": 12,
+    "dropout": 0.1
+  },
+  "vocab": {
+    ";": 1,
+    ":": 2,
+    ",": 3,
+    ".": 4,
+    "!": 5,
+    "?": 6,
+    "—": 9,
+    "…": 10,
+    "\"": 11,
+    "(": 12,
+    ")": 13,
+    "“": 14,
+    "”": 15,
+    " ": 16,
+    "\u0303": 17,
+    "ʣ": 18,
+    "ʥ": 19,
+    "ʦ": 20,
+    "ʨ": 21,
+    "ᵝ": 22,
+    "\uAB67": 23,
+    "A": 24,
+    "I": 25,
+    "O": 31,
+    "Q": 33,
+    "S": 35,
+    "T": 36,
+    "W": 39,
+    "Y": 41,
+    "ᵊ": 42,
+    "a": 43,
+    "b": 44,
+    "c": 45,
+    "d": 46,
+    "e": 47,
+    "f": 48,
+    "h": 50,
+    "i": 51,
+    "j": 52,
+    "k": 53,
+    "l": 54,
+    "m": 55,
+    "n": 56,
+    "o": 57,
+    "p": 58,
+    "q": 59,
+    "r": 60,
+    "s": 61,
+    "t": 62,
+    "u": 63,
+    "v": 64,
+    "w": 65,
+    "x": 66,
+    "y": 67,
+    "z": 68,
+    "ɑ": 69,
+    "ɐ": 70,
+    "ɒ": 71,
+    "æ": 72,
+    "β": 75,
+    "ɔ": 76,
+    "ɕ": 77,
+    "ç": 78,
+    "ɖ": 80,
+    "ð": 81,
+    "ʤ": 82,
+    "ə": 83,
+    "ɚ": 85,
+    "ɛ": 86,
+    "ɜ": 87,
+    "ɟ": 90,
+    "ɡ": 92,
+    "ɥ": 99,
+    "ɨ": 101,
+    "ɪ": 102,
+    "ʝ": 103,
+    "ɯ": 110,
+    "ɰ": 111,
+    "ŋ": 112,
+    "ɳ": 113,
+    "ɲ": 114,
+    "ɴ": 115,
+    "ø": 116,
+    "ɸ": 118,
+    "θ": 119,
+    "œ": 120,
+    "ɹ": 123,
+    "ɾ": 125,
+    "ɻ": 126,
+    "ʁ": 128,
+    "ɽ": 129,
+    "ʂ": 130,
+    "ʃ": 131,
+    "ʈ": 132,
+    "ʧ": 133,
+    "ʊ": 135,
+    "ʋ": 136,
+    "ʌ": 138,
+    "ɣ": 139,
+    "ɤ": 140,
+    "χ": 142,
+    "ʎ": 143,
+    "ʒ": 147,
+    "ʔ": 148,
+    "ˈ": 156,
+    "ˌ": 157,
+    "ː": 158,
+    "ʰ": 162,
+    "ʲ": 164,
+    "↓": 169,
+    "→": 171,
+    "↗": 172,
+    "↘": 173,
+    "ᵻ": 177
+  }
+}

kokoro/kokoro-v1_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4
+size 327212226

kokoro/voices/af_heart.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab5709b8ffab19bfd849cd11d98f75b60af7733253ad0d67b12382a102cb4ff
+size 523425

loras/LTX-2.3-Licon-MSR-V1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4008d341c58791659a9b3840ac8d76f08d8941f82670dc2d3dad0f71876bbae5
+size 654443424

loras/LTX-2.3-Licon-MSR-V2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f61d3b5c61b160c409b45ebaa72fd7ab9bb38bf3bf7f09edaddc87762d5fa98
+size 654443392

loras/Ltx2.3-Licon-VBVR-I2V-96000-R32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5ff61d3e2959babf01112a8d7f00776273415573aa29a82f2af00070fd1408
+size 554006432

loras/omninft-ltx2-19b-rl-lora-r32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7927a790774bb21c0a90490c775b37f88275d52e04ce6d5c6d267b0dbdb0a87
+size 1233687664

loras/omninft-ltx2.3-22b-rl-lora-r32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e266785d020e23dfe7b3d3a486e41d76d58b0b3a8923711095b9badcd71bc1
+size 1233687664