Add files using upload-large-folder tool

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

NOTICE

@@ -0,0 +1,23 @@
+Gemma 4 31B Instruct
+Copyright (c) Google DeepMind
+
+Original model weights: https://huggingface.co/google/gemma-4-31B-it
+Distributed by Google DeepMind under the Apache License 2.0
+(https://ai.google.dev/gemma/apache_2).
+
+This repository contains a derivative work: an INT8 W8A8 post-training quantized
+version of the above model, produced with AMD Quark
+(https://github.com/amd/quark). The original BF16 weights have been transformed
+into INT8 per-channel weights with per-token dynamic INT8 activations; the
+embedding, lm_head and the entire vision tower remain in BF16.
+
+Modifications made:
+  - Linear weights of the language tower converted from BF16 to INT8 with
+    per-output-channel symmetric scales.
+  - quantization_config block appended to config.json (custom_mode='quark',
+    pack_method='order', weight_format='real_quantized').
+  - All other tokenizer / processor / chat_template files are unchanged from
+    the upstream google/gemma-4-31B-it release.
+
+The license, attribution and disclaimer of warranty terms of the Apache License
+2.0 (see LICENSE) apply to both the original work and this derivative.

README.md

@@ -0,0 +1,183 @@
+---
+license: apache-2.0
+library_name: transformers
+language:
+  - en
+pipeline_tag: text-generation
+base_model: google/gemma-4-31B-it
+tags:
+  - gemma
+  - gemma4
+  - quantized
+  - int8
+  - w8a8
+  - quark
+  - vllm
+  - conversational
+  - text-generation-inference
+---
+
+# Gemma-4-31B-it-Quark-W8A8-INT8
+
+W8A8 INT8 quantized version of [google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it) using [AMD Quark](https://github.com/amd/quark).
+
+## Model Details
+
+|                |                                                                                |
+|----------------|--------------------------------------------------------------------------------|
+| Base Model     | `google/gemma-4-31B-it`                                                        |
+| Architecture   | `Gemma4ForConditionalGeneration` (multimodal: text + vision)                   |
+| Parameters     | 31 B text decoder (quantized) + vision tower & embeddings kept in BF16          |
+| Quantization   | W8A8 INT8 (per-channel weight + per-token dynamic activation)                  |
+| Quantizer      | AMD Quark `0.11.1` (`ptpc_int8` scheme, `pack_method='order'`)                 |
+| Model Size     | ~32 GB (single `model.safetensors`)                                            |
+| Original Size  | ~62.5 GB (BF16)                                                                |
+| Compression    | ~2× size reduction                                                             |
+
+### Quantization Scheme
+
+| Component   | dtype | Granularity                | Mode               |
+|-------------|-------|----------------------------|--------------------|
+| Weight      | INT8  | per-channel (`ch_axis=0`)  | symmetric, static  |
+| Activation  | INT8  | per-token (`ch_axis=1`)    | symmetric, dynamic |
+| `lm_head`   | BF16  | —                          | unquantized        |
+| `embed_tokens` | BF16 | —                         | unquantized        |
+| `vision_tower` / `embed_vision` | BF16 | — | unquantized (multimodal preserved) |
+
+## Accuracy
+
+GSM8K 8-shot evaluation on the full 1319-question test split (vLLM, `temperature=0`, `concurrency=16`, `max_tokens=512`, standard chat template with `####` answer format):
+
+| Model                                  | Scheme                              | Accuracy   | Correct      |
+|----------------------------------------|-------------------------------------|------------|--------------|
+| `google/gemma-4-31B-it` (BF16 baseline) | —                                   | **96.74%** | 1276 / 1319  |
+| **This model (Quark W8A8 INT8)**       | per-channel weight + per-token act. | **96.66%** | 1275 / 1319  |
+
+Δ vs BF16: **−0.08pp (essentially lossless)**.
+
+## How to Use
+
+### With vLLM (Recommended)
+
+```bash
+# Start the server (single MI300X / MI350X / MI355X is enough; A100-80G also works)
+vllm serve nameistoken/Gemma-4-31B-it-Quark-W8A8-INT8 \
+    --tensor-parallel-size 1 \
+    --max-model-len 8192 \
+    --gpu-memory-utilization 0.9 \
+    --trust-remote-code
+
+# Chat completion
+curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
+  "model": "nameistoken/Gemma-4-31B-it-Quark-W8A8-INT8",
+  "messages": [{"role": "user", "content": "Hello! What is the capital of France?"}],
+  "max_tokens": 256,
+  "temperature": 0.7
+}'
+```
+
+### Hardware Requirements
+
+- **Minimum**: 1× GPU with ≥48 GB VRAM (e.g., AMD MI300X / MI350X / MI355X, NVIDIA A100-80G / H100).
+- For longer context or larger batches use TP=2 across two of the same GPUs.
+
+## Quantization Details
+
+This model was quantized using AMD Quark's per-token per-channel INT8 scheme:
+
+- **Weight quantization**: INT8 per-channel (one scale per output channel), symmetric, static.
+- **Activation quantization**: INT8 per-token (one scale per token), symmetric, dynamic (computed at inference time).
+- **Excluded layers**: `lm_head`, `*embed_tokens*`, `*vision_tower*`, `*embed_vision*` (output head + token embedding + the entire vision tower remain in BF16).
+- **Export**: `pack_method='order'`, `weight_format='real_quantized'`, `custom_mode='quark'` → real INT8 weights with BF16 scales (no fake-quant, no zero-point).
+
+### Reproduce Quantization
+
+```bash
+# 1. Environment
+pip install amd-quark==0.11.1 datasets accelerate
+git clone https://github.com/huggingface/transformers.git
+cd transformers && pip install -e . --no-deps   # transformers main (>= 5.6.0.dev0)
+```
+
+```python
+# quark_gemma4_int8.py
+import os, torch
+from transformers import AutoTokenizer, Gemma4ForConditionalGeneration
+from quark.torch import ModelQuantizer
+from quark.torch.quantization.config.config import (
+    QTensorConfig, QuantizationConfig, Config, Dtype,
+)
+from quark.torch.quantization.config.type import (
+    RoundType, ScaleType, QSchemeType,
+)
+from quark.torch.quantization.observer import PerChannelMinMaxObserver
+
+MODEL_IN  = "google/gemma-4-31B-it"
+MODEL_OUT = "./Gemma-4-31B-it-Quark-W8A8-INT8"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_IN, trust_remote_code=True)
+model = Gemma4ForConditionalGeneration.from_pretrained(
+    MODEL_IN, torch_dtype=torch.bfloat16,
+    device_map="auto", trust_remote_code=True,
+)
+
+weight_spec = QTensorConfig(
+    dtype=Dtype.int8, observer_cls=PerChannelMinMaxObserver,
+    symmetric=True, is_dynamic=False,
+    qscheme=QSchemeType.per_channel, ch_axis=0,
+    round_method=RoundType.round, scale_type=ScaleType.float,
+)
+input_spec = QTensorConfig(
+    dtype=Dtype.int8, observer_cls=PerChannelMinMaxObserver,
+    symmetric=True, is_dynamic=True,
+    qscheme=QSchemeType.per_channel, ch_axis=1,
+    round_method=RoundType.round, scale_type=ScaleType.float,
+)
+
+q_cfg = Config(
+    global_quant_config=QuantizationConfig(
+        input_tensors=input_spec, weight=weight_spec,
+    ),
+    exclude=[
+        "lm_head", "*embed_tokens*",
+        "*vision_tower*", "*embed_vision*",
+    ],
+)
+
+quantizer = ModelQuantizer(q_cfg, multi_device=True)
+model = quantizer.quantize_model(model, dataloader=None)  # PTQ, no calibration data needed for dynamic act
+quantizer.freeze(model)
+
+quantizer.export_model(
+    model, MODEL_OUT,
+    pack_method="order",
+    weight_format="real_quantized",
+    custom_mode="quark",
+)
+tokenizer.save_pretrained(MODEL_OUT)
+```
+
+## Citation
+
+If you use this model, please cite the original Gemma 4 release:
+
+```bibtex
+@misc{google2026gemma4,
+  title  = {Gemma 4},
+  author = {Google DeepMind},
+  year   = {2026},
+  url    = {https://huggingface.co/google/gemma-4-31B-it}
+}
+```
+
+## License
+
+This model is released under the **[Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)**, following the [Gemma 4 license](https://ai.google.dev/gemma/apache_2) under which the upstream `google/gemma-4-31B-it` weights are distributed by Google DeepMind.
+
+This is a quantized derivative of `google/gemma-4-31B-it`. Per Apache 2.0 §4:
+
+- Modified files (the INT8-quantized `model.safetensors` and the appended `quantization_config` block in `config.json`) carry this notice as part of the model card.
+- Original copyright and attribution notices from the base model are preserved (see `NOTICE`).
+- A copy of the Apache 2.0 license text is included as `LICENSE`.
+
+Original weights © Google DeepMind. Quantization performed by the model author; no warranty of any kind is provided (see `LICENSE` §7–8).

chat_template.jinja

@@ -0,0 +1,347 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- 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 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([])) -}}
+                    }
+                {%- 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'] -%}
+        {{- messages[0]['content'] | trim -}}
+        {%- 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 -%}
+
+            {%- 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 -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif not (ns_tr_out.flag and not message.get('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 +1,424 @@
+{
+  "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
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "quantization_config": {
+    "algo_config": null,
+    "exclude": [
+      "model.vision_tower.patch_embedder.input_proj",
+      "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.0.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.0.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.1.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.1.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.2.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.2.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.3.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.3.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.4.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.4.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.5.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.5.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.6.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.6.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.7.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.7.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.8.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.8.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.9.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.9.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.10.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.10.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.11.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.11.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.12.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.12.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.13.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.13.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.14.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.14.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.15.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.15.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.16.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.16.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.17.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.17.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.18.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.18.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.19.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.19.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.20.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.20.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.21.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.21.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.22.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.22.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.23.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.23.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.24.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.24.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.25.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.25.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.26.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.26.mlp.down_proj.linear",
+      "model.embed_vision.embedding_projection",
+      "lm_head"
+    ],
+    "export": {
+      "kv_cache_group": [],
+      "min_kv_scale": 0.0,
+      "pack_method": "order",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "global_quant_config": {
+      "bias": null,
+      "input_tensors": {
+        "ch_axis": 1,
+        "dtype": "int8",
+        "group_size": null,
+        "is_dynamic": true,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerChannelMinMaxObserver",
+        "qscheme": "per_channel",
+        "round_method": "round",
+        "scale_calculation_mode": null,
+        "scale_format": null,
+        "scale_type": "float",
+        "symmetric": true
+      },
+      "output_tensors": null,
+      "target_device": null,
+      "weight": {
+        "ch_axis": 0,
+        "dtype": "int8",
+        "group_size": null,
+        "is_dynamic": false,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerChannelMinMaxObserver",
+        "qscheme": "per_channel",
+        "round_method": "round",
+        "scale_calculation_mode": null,
+        "scale_format": null,
+        "scale_type": "float",
+        "symmetric": true
+      }
+    },
+    "kv_cache_post_rope": false,
+    "kv_cache_quant_config": {},
+    "layer_quant_config": {},
+    "layer_type_quant_config": {},
+    "quant_method": "quark",
+    "quant_mode": "eager_mode",
+    "softmax_quant_spec": null,
+    "version": "0.11.1"
+  },
+  "text_config": {
+    "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,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 5376,
+    "hidden_size_per_layer_input": 0,
+    "initializer_range": 0.02,
+    "intermediate_size": 21504,
+    "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",
+      "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": null,
+    "num_attention_heads": 32,
+    "num_experts": null,
+    "num_global_key_value_heads": 4,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 16,
+    "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
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.0.dev0",
+  "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": "5.6.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc23ef9a67dd909effef1d26b6fc2d9b13def70d0aa2f4ccccb07b512c41aaa
+size 33268121104

processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "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
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

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": 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": "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>"
+}