Upload Gemma4 26B MoE QAT Q4 MLX model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,91 @@
+---
+library_name: mlx
+license: apache-2.0
+license_link: https://ai.google.dev/gemma/docs/gemma_4_license
+pipeline_tag: image-text-to-text
+base_model: google/gemma-4-26B-A4B-it-qat-q4_0-gguf
+tags:
+- mlx
+- gemma4
+- qat
+- q4
+- moe
+- apple-silicon
+---
+
+# mavis-ai/Gemma4-26B-MoE-QATQ4
+
+This repository provides an MLX-ready **QAT Q4** build of Google's Gemma 4 26B A4B instruction-tuned Mixture-of-Experts model for local inference on Apple Silicon Macs.
+
+Unlike a plain post-training 4-bit quantized checkpoint, this model is based on Google's **Quantization-Aware Training (QAT)** Q4 release. The goal is not only to reduce the storage and memory footprint, but also to preserve the model's practical judgment, instruction-following behavior, and reasoning stability under low-bit inference.
+
+**💡 Notice for Everyone**
+While this repository is hosted primarily as a dedicated engine source for our application ecosystem (**R.E.V.I.S.**), **you are completely free to download and use this model normally** for your own local MLX projects or workflows.
+
+For more details on the official source model, please refer to Google's Gemma 4 model pages:
+
+- [google/gemma-4-26B-A4B-it](https://huggingface.co/google/gemma-4-26B-A4B-it)
+- [google/gemma-4-26B-A4B-it-qat-q4_0-gguf](https://huggingface.co/google/gemma-4-26B-A4B-it-qat-q4_0-gguf)
+
+## Why QAT Q4?
+
+R.E.V.I.S. is designed around local, evidence-grounded AI workflows where the model does not need to memorize everything. Instead, the model should be strong at judging, reading, filtering, structuring, and reasoning over the local context it is given.
+
+QAT Q4 is especially interesting for this direction because it aims to keep more of the model's behavior intact after quantization, compared with ordinary post-training quantization. In practical local workflows, this can matter for tasks such as:
+
+- judging whether a passage is real body text or navigation / advertisement noise
+- checking whether a Markdown extraction is complete enough for RAG
+- preserving instruction-following behavior in low-bit inference
+- restructuring long documents into useful sections
+- acting as a second-opinion evaluator for local agents
+
+## 🚀 Optimized for R.E.V.I.S. (Local Cognitive OS)
+
+We prepared and tested this QAT Q4 model to serve as a local reasoning and judgment engine for **R.E.V.I.S.**
+
+**R.E.V.I.S.** is a 100% local Cognitive OS for Multi-Agentic AI. It transforms your Mac devices into a distributed Agentic Swarm via zero-config Wi-Fi clustering, allowing you to run heavy AI workloads—like recursive web research, dynamic RAG generation, and multi-step logic—without killing single-machine performance.
+
+If you are interested in pushing the limits of local AI and open-weight models like this one, check out our project!
+
+- **🌐 Official Website:** [https://mavis-ai.co.jp/revis/](https://mavis-ai.co.jp/revis/)
+- **▶️ Watch the 13-min Raw Demo (Multi-node Dynamic RAG):** [https://x.gd/LxaBF](https://x.gd/LxaBF)
+- **🐦 Follow our updates on X:** [@mavis_ai_jp](https://x.com/mavis_ai_jp)
+
+## Usage
+
+Install or update the MLX runtime you use for Gemma 4 / multimodal models:
+
+```bash
+pip install -U mlx mlx-lm mlx-vlm huggingface_hub hf_xet
+```
+
+Download the model:
+
+```bash
+hf download mavis-ai/Gemma4-26B-MoE-QATQ4 \
+  --local-dir ~/Models/mlx/Gemma4-26B-MoE-QATQ4
+```
+
+Run a quick text generation test:
+
+```bash
+python -m mlx_vlm.generate \
+  --model ~/Models/mlx/Gemma4-26B-MoE-QATQ4 \
+  --max-tokens 256 \
+  --temperature 0.0 \
+  --prompt "日本語で短く自己紹介してください。"
+```
+
+## Notes
+
+Gemma 4 26B A4B is a Mixture-of-Experts model. Although only a subset of parameters is active per token, the full model still needs to be stored and loaded. On Apple Silicon, practical speed and context length depend heavily on unified memory size, MLX / mlx-vlm versions, prompt length, KV cache usage, and generation settings.
+
+For day-to-day local RAG, a smaller Gemma 4 E2B / E4B QAT model may be faster. This 26B MoE QAT Q4 build is best suited for heavier judgment tasks, long-document inspection, extraction-quality review, and second-opinion reasoning.
+
+## License
+
+This model is a derivative of Google's Gemma 4 26B A4B instruction-tuned QAT Q4 release, which is distributed by Google under the **Apache License 2.0**.
+
+This derivative is likewise distributed under the Apache License 2.0. A copy of the license is included in the `LICENSE` file in this repository, and can also be found at <https://www.apache.org/licenses/LICENSE-2.0>.
+
+**Modification notice:** This repository adapts the official Gemma 4 26B A4B instruction-tuned QAT Q4 model for MLX-based local inference. No additional fine-tuning or architectural changes were applied by MAVIS.

chat_template.jinja

@@ -0,0 +1,354 @@
+{%- 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 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 -%}
+
+{%- set ns = namespace(prev_message_type=None) -%}
+{%- set loop_messages = messages -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking is defined and enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if 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: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
+    {%- set prev_nt = namespace(role=None, found=false) -%}
+    {%- if loop.index0 > 0 -%}
+        {%- for j in range(loop.index0 - 1, -1, -1) -%}
+            {%- if not prev_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
+                    {%- set prev_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- set continue_same_model_turn = (role == 'model' and prev_nt.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') -%}
+    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message['tool_calls'] -%}
+                {%- for tool_call in message['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 string -%}
+                        {{- function['arguments'] -}}
+                    {%- 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['tool_responses'] -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), 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') | default('unknown')) -%}
+                        {%- for tc in message['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) -}}
+                        {%- 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['content'] is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item['type'] == 'image' -%}
+                        {{- '<|image|>' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '<|video|>' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif not (ns_tr_out.flag and not has_content) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+    {%- 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 | default(false) -%}
+            {{- '<|channel>thought\n<channel|>' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,1117 @@
+{
+    "architectures": [
+        "Gemma4ForConditionalGeneration"
+    ],
+    "audio_config": null,
+    "audio_token_id": 258881,
+    "boa_token_id": 256000,
+    "boi_token_id": 255999,
+    "dtype": "bfloat16",
+    "eoa_token_id": 258883,
+    "eoa_token_index": 258883,
+    "eoi_token_id": 258882,
+    "eos_token_id": [
+        1,
+        106,
+        50
+    ],
+    "image_token_id": 258880,
+    "initializer_range": 0.02,
+    "model_type": "gemma4",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.0.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.1.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.2.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.3.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.4.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.5.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.6.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.7.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.8.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.9.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.10.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.11.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.12.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.13.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.14.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.15.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.16.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.17.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.18.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.19.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.20.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.21.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.22.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.23.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.24.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.25.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.26.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.27.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.28.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "language_model.model.layers.29.router.proj": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attention_k_eq_v": true,
+        "bos_token_id": 2,
+        "dtype": "bfloat16",
+        "enable_moe_block": true,
+        "eos_token_id": 1,
+        "final_logit_softcapping": 30.0,
+        "global_head_dim": 512,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 2816,
+        "hidden_size_per_layer_input": 0,
+        "initializer_range": 0.02,
+        "intermediate_size": 2112,
+        "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"
+        ],
+        "max_position_embeddings": 262144,
+        "model_type": "gemma4_text",
+        "moe_intermediate_size": 704,
+        "num_attention_heads": 16,
+        "num_experts": 128,
+        "num_global_key_value_heads": 2,
+        "num_hidden_layers": 30,
+        "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": 8,
+        "use_bidirectional_attention": "vision",
+        "use_cache": true,
+        "use_double_wide_mlp": false,
+        "vocab_size": 262144,
+        "vocab_size_per_layer_input": 262144
+    },
+    "tie_word_embeddings": true,
+    "transformers_version": "5.6.2",
+    "video_token_id": 258884,
+    "vision_config": {
+        "_name_or_path": "",
+        "architectures": null,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "chunk_size_feed_forward": 0,
+        "default_output_length": 280,
+        "dtype": "bfloat16",
+        "global_head_dim": 72,
+        "head_dim": 72,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "intermediate_size": 4304,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "max_position_embeddings": 131072,
+        "model_type": "gemma4_vision",
+        "num_attention_heads": 16,
+        "num_hidden_layers": 27,
+        "num_key_value_heads": 16,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "patch_size": 16,
+        "pooling_kernel_size": 3,
+        "position_embedding_size": 10240,
+        "problem_type": null,
+        "return_dict": true,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "rope_theta": 100.0,
+            "rope_type": "default"
+        },
+        "standardize": true,
+        "use_clipped_linears": false
+    },
+    "vision_soft_tokens_per_image": 280
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.6.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898863f0d5eba7153a9c9b9443aac1969809f2149e88481c725b6da40783f129
+size 5275612587

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2abdca76ed4a647cfe8af680908894e2709b4e1221ddbbbef1b1edb14f60e303
+size 5296718232

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a554f0fdb61bc9e510a5318e723a780c31434fd3e3dcdd3c16c700f835ade7b7
+size 5036507755

processor_config.json

@@ -0,0 +1,42 @@
+{
+  "audio_seq_length": 750,
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 224,
+      "width": 224
+    }
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "feature_extractor": {
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "sampling_rate": 16000,
+    "num_mel_filters": 128,
+    "fft_length": 512,
+    "hop_length": 160,
+    "chunk_duration": 8.0,
+    "overlap_duration": 1.0
+  },
+  "audio_ms_per_token": 40
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,96 @@
+{
+  "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": true,
+  "local_files_only": true,
+  "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": "Gemma4Processor",
+  "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\\>)?"
+  },
+  "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>"
+}