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 2026 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

NOTICE

@@ -0,0 +1,39 @@
+Qwen3.6-35B-A3B-Quark-W8A8-INT8
+Copyright (c) 2025-2026 Qwen Team, Alibaba Cloud
+
+Original model weights: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
+Distributed by Alibaba Cloud under the Apache License, Version 2.0.
+
+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 language-tower weights have
+been transformed into INT8 per-channel weights with per-token dynamic INT8
+activations. The embeddings, lm_head, MoE router (mlp.gate), per-layer
+shared_expert_gate, the entire 27-block ViT vision tower, and the MTP head
+all remain in BF16.
+
+Modifications made:
+
+  - Qwen3_5MoeExperts fused gate_up_proj / down_proj tensors were split
+    in-place into ModuleList[256] of per-expert nn.Linear triplets so they
+    could be observed by Quark; the resulting key layout is bit-compatible
+    with vLLM's FusedMoE.make_expert_params_mapping (no loader changes).
+  - Linear weights of the language tower were converted from BF16 to INT8
+    with per-output-channel symmetric scales. Activations use per-token
+    symmetric dynamic INT8 at runtime.
+  - A quantization_config block was appended to config.json
+    (quant_method='quark', custom_mode='quark', pack_method='order',
+    weight_format='real_quantized').
+  - Quark-native quantizer key names were renamed to the vLLM/HF-standard
+    layout:
+      * *_quantizer.scale      -> *_scale
+      * *_quantizer.zero_point -> dropped (symmetric quantization)
+      * weight_scale squeezed from shape [out, 1] to [out].
+  - Shards were re-packed into 7 x ~5 GB files with a matching
+    model.safetensors.index.json.
+  - All tokenizer / preprocessor / chat_template / generation_config files
+    are byte-identical to the upstream Qwen/Qwen3.6-35B-A3B release.
+
+The license, attribution and disclaimer-of-warranty terms of the upstream
+Apache-2.0 license (see LICENSE) apply to both the original work and this
+derivative.

README.md

@@ -0,0 +1,215 @@
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE
+library_name: transformers
+language:
+  - en
+pipeline_tag: image-text-to-text
+base_model: Qwen/Qwen3.6-35B-A3B
+tags:
+  - qwen3_5_moe
+  - moe
+  - mixture-of-experts
+  - quantized
+  - int8
+  - w8a8
+  - quark
+  - vllm
+  - conversational
+  - text-generation-inference
+  - image-text-to-text
+---
+
+# Qwen3.6-35B-A3B-Quark-W8A8-INT8
+
+W8A8 INT8 quantized version of [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) produced with [AMD Quark](https://github.com/amd/quark).
+
+## Model Details
+
+|                    |                                                                                     |
+|--------------------|-------------------------------------------------------------------------------------|
+| Base Model         | `Qwen/Qwen3.6-35B-A3B`                                                              |
+| Architecture       | `Qwen3_5MoeForConditionalGeneration` (multimodal: ViT vision + text MoE + MTP head) |
+| Parameters         | 35B total / 3B activated per token (256 experts, top-8) + 27-block ViT (BF16)       |
+| Quantization       | W8A8 INT8 — per-channel weight + per-token dynamic activation                       |
+| Quantizer          | AMD Quark `0.11.1` (`pack_method='order'`, `weight_format='real_quantized'`)        |
+| Model Size         | ~35 GB (7 shards of ~5 GB)                                                          |
+| Original Size      | ~67 GB (BF16, 26 shards)                                                            |
+| Compression        | ~1.93× size reduction                                                               |
+
+### Quantization Scheme
+
+| Component                                               | dtype | Granularity                 | Mode                |
+|---------------------------------------------------------|-------|-----------------------------|---------------------|
+| Language attention (`q/k/v/o_proj`, `linear_attn.*`)    | INT8  | per-channel weight (axis=0) | weight static       |
+| Language MoE experts (256 × `gate/up/down_proj` × 40)   | INT8  | per-channel weight (axis=0) | weight static       |
+| `shared_expert` (`gate/up/down_proj`)                   | INT8  | per-channel weight (axis=0) | weight static       |
+| All activations above                                   | INT8  | per-token (axis=1)          | **dynamic**         |
+| `lm_head`                                               | BF16  | —                           | unquantized         |
+| `embed_tokens`                                          | BF16  | —                           | unquantized         |
+| MoE router (`mlp.gate`) — top-k gate                    | BF16  | —                           | unquantized         |
+| `shared_expert_gate`                                    | BF16  | —                           | unquantized         |
+| `visual.*` (27-block ViT + merger)                      | BF16  | —                           | unquantized         |
+| MTP head                                                | BF16  | —                           | unquantized         |
+
+> **Note**: MoE experts are stored as 256 per-expert `nn.Linear` triplets (`gate_proj/up_proj/down_proj`) instead of the upstream fused `gate_up_proj` tensor. This is required so that Quark observers can attach to each expert as a standard `nn.Linear`, and the key layout matches vLLM's `FusedMoE.make_expert_params_mapping` exactly — no loader-side change needed.
+
+## Accuracy
+
+GSM8K full **1319**-question test split, served under vLLM, `/v1/chat/completions` with `chat_template_kwargs.enable_thinking=false`, `temperature=0`, `concurrency=16`, `max_tokens=1024`.
+
+| Model                                    | Accuracy    | Correct      |
+|------------------------------------------|------------:|-------------:|
+| `Qwen/Qwen3.6-35B-A3B` (BF16 baseline)   | **95.91 %** | 1265 / 1319  |
+| **This model (Quark W8A8 INT8)**         | **95.91 %** | 1265 / 1319  |
+
+**Δ vs BF16 = 0.00 pp.** The two result sets overlap on 1250 / 1280 questions (Jaccard = 0.9766); each side wins 15 problems the other loses — no systematic regression.
+
+Both runs were done on a single AMD MI355X (288 GB HBM3e) at `gpu_memory_utilization=0.55` (BF16) / `0.85` (INT8), `max_model_len=4096`.
+
+## Performance
+
+Measured on a single AMD **Radeon 8060S APU (gfx1151, "Strix Halo")** with 128 GB LPDDR5X-8000 unified memory, container `kyuz0/vllm-therock-gfx1151:stable` (vLLM `0.19.2rc1.dev113+g6aa057c9d`, transformers `5.5.4`), TP=1, KV cache BF16 (gfx1151 has no INT8 matrix core).
+
+### Long context — `input=4000 / output=200`, `num_prompts = C * 3`
+
+`--max-model-len 4096 --gpu-memory-utilization 0.85`. BF16 baseline is the upstream Qwen3.6-35B-A3B (~67 GB weights).
+
+| Concurrency | BF16 req/s | BF16 out tok/s | Quark W8A8 req/s | Quark W8A8 out tok/s | W8A8 / BF16 |
+|------------:|-----------:|---------------:|-----------------:|---------------------:|:-----------:|
+|  1          | 0.044      |  8.83          | **0.060**        | **12.02**            | **+36%**    |
+|  5          | 0.093      | 18.58          | **0.142**        | **28.31**            | **+52%**    |
+| 10          | 0.128      | 25.58          | **0.186**        | **37.30**            | **+46%**    |
+| 20          | 0.163      | 32.53          | **0.240**        | **47.98**            | **+48%**    |
+
+### Short context — `input=512 / output=128`, `--ignore-eos`, bs = num_prompts
+
+Typical chat / decode-bound workload:
+
+| Batch size | BF16 out tok/s | Quark W8A8 out tok/s | W8A8 / BF16 |
+|-----------:|---------------:|---------------------:|:-----------:|
+|  1         | 13.36          | **17.43**            | **+30%**    |
+|  8         | 36.47          | **64.91**            | **+78%**    |
+| 16         | 61.16          | **92.04**            | **+50%**    |
+
+### Takeaways
+
+- **Quark W8A8 beats BF16 at every concurrency we measured on gfx1151**, by +30–78 %. The gfx1151 APU has no INT8 matrix core, so the gain comes from the ~2× smaller weight footprint cutting memory-bandwidth pressure (LPDDR5X is the dominant bottleneck on Strix Halo).
+- **Decode-bound / short-context is where W8A8 shines the most**: at 512 in / 128 out, bs=8 → +78 %. Prefill-heavy long contexts still benefit, just less dramatically.
+- **Fits in unified memory with headroom**: the packed INT8 model is ~35 GB vs ~67 GB BF16, so KV cache and weights no longer compete on a 128 GB Strix Halo box (the BF16 build hit a scheduler regression around C=100 where TTFT blew up to ~187 s — W8A8 avoids that class of pressure entirely).
+
+## How to Use
+
+### With vLLM (Recommended)
+
+```bash
+vllm serve /path/to/Qwen3.6-35B-A3B-Quark-W8A8-INT8 \
+    --served-model-name Qwen3.6-35B-A3B-W8A8 \
+    --tensor-parallel-size 1 \
+    --max-model-len 4096 \
+    --gpu-memory-utilization 0.85 \
+    --trust-remote-code \
+    --port 8000
+
+curl http://localhost:8000/v1/chat/completions \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "model": "Qwen3.6-35B-A3B-W8A8",
+    "messages": [{"role":"user","content":"Solve: 16 - 3 - 4 = ?"}],
+    "max_tokens": 256, "temperature": 0.7,
+    "chat_template_kwargs": {"enable_thinking": false}
+  }'
+```
+
+- vLLM ≥ `0.19.2rc1` with the `qwen3_5_moe` registration is required.
+- The Qwen3.6 default chat template wraps the response in `<think>...</think>`; pass `enable_thinking=false` if you want the short form.
+
+### Hardware Requirements
+
+- **Minimum VRAM**: ~40 GB free for model weights + KV cache, i.e. a single MI300X / MI355X / H100-80G / A100-80G.
+- Can fit on a consumer-class 48 GB card (e.g. W7900D) at `max_model_len` ≤ 4096, whereas the BF16 original (~68 GB of weights) cannot.
+
+## Quantization Details
+
+### Excluded layers (kept BF16)
+
+- `lm_head`
+- `model.language_model.layers.*.mlp.shared_expert_gate` (40 × single-output gate)
+- `model.visual.pos_embed`, `model.visual.blocks.*.attn.{qkv,proj}`, `model.visual.blocks.*.mlp.linear_fc{1,2}`, `model.visual.merger.linear_fc{1,2}` (full 27-block ViT + merger)
+- `model.embed_tokens` (not an `nn.Linear`; naturally not touched)
+- MoE top-k router `mlp.gate` — kept BF16 via the custom MoE rewrite (see below)
+- MTP head — kept BF16
+
+### Pre-quantization rewrite
+
+The upstream `Qwen3_5MoeExperts` module stores 256 experts as a single fused 3-D tensor (`gate_up_proj: [E, 2·I, H]`, `down_proj: [E, H, I]`). Before quantization this is split in-place into `ModuleList[256]` of three `nn.Linear`s per expert, following the SwiGLU `chunk(2, dim=-1)` semantics (front half = `gate`, back half = `up`). This makes every expert visible to Quark as a standard `nn.Linear`, and the resulting key layout is bit-compatible with vLLM's fused MoE loader.
+
+### Post-export rename
+
+Quark's native `custom_mode='quark'` export emits `*_quantizer.scale` / `*_quantizer.zero_point` keys. The published shards here have already been converted to the vLLM/HF-compatible layout:
+
+- `*_quantizer.scale` → `*_scale`
+- `*_quantizer.zero_point` → dropped (symmetric quant)
+- `weight_scale` squeezed from `[out, 1]` to `[out]`
+
+### Reproduce
+
+A full walkthrough (Docker image, Quark config, MoE split, post-export rename, vLLM serve, GSM8K eval) is documented at <https://github.com/JoursBleu/docs/blob/master/qwen3.5/Qwen3.6-35B-A3B_Quark_W8A8_quantization_guide.md>.
+
+Core Quark config fragment:
+
+```python
+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
+
+weight = 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,
+)
+act = 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,
+)
+cfg = Config(
+    global_quant_config=QuantizationConfig(weight=weight, input_tensors=act),
+    exclude=[
+        "lm_head",
+        "*mlp.gate",              # MoE router
+        "*shared_expert_gate",    # per-layer gate
+        "*visual*",               # vision tower + merger
+        "mtp*",                   # MTP head
+    ],
+)
+```
+
+Export with `pack_method='order'`, `weight_format='real_quantized'`, `custom_mode='quark'`, then run the `rename_keys.py` post-processor.
+
+## Citation
+
+```bibtex
+@misc{qwen35moe,
+  title  = {Qwen3.6-35B-A3B},
+  author = {Qwen Team, Alibaba Cloud},
+  year   = {2026},
+  url    = {https://huggingface.co/Qwen/Qwen3.6-35B-A3B}
+}
+```
+
+## License
+
+This model is released under the **Apache License, Version 2.0**, following the upstream
+[`Qwen/Qwen3.6-35B-A3B`](https://huggingface.co/Qwen/Qwen3.6-35B-A3B).
+
+- Modified files (the INT8-quantized `model-*.safetensors` and the `quantization_config` block in `config.json`) are described in `NOTICE`.
+- A copy of the Apache-2.0 license is provided in `LICENSE`.
+
+Original weights © 2025–2026 Qwen Team, Alibaba Cloud. Quantization is a derivative work distributed under Apache-2.0; no warranty of any kind is provided.

chat_template.jinja

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

config.json

@@ -0,0 +1,328 @@
+{
+  "architectures": [
+    "Qwen3_5MoeForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "model_type": "qwen3_5_moe",
+  "quantization_config": {
+    "algo_config": null,
+    "exclude": [
+      "model.visual.pos_embed",
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.language_model.layers.0.mlp.shared_expert_gate",
+      "model.language_model.layers.1.mlp.shared_expert_gate",
+      "model.language_model.layers.2.mlp.shared_expert_gate",
+      "model.language_model.layers.3.mlp.shared_expert_gate",
+      "model.language_model.layers.4.mlp.shared_expert_gate",
+      "model.language_model.layers.5.mlp.shared_expert_gate",
+      "model.language_model.layers.6.mlp.shared_expert_gate",
+      "model.language_model.layers.7.mlp.shared_expert_gate",
+      "model.language_model.layers.8.mlp.shared_expert_gate",
+      "model.language_model.layers.9.mlp.shared_expert_gate",
+      "model.language_model.layers.10.mlp.shared_expert_gate",
+      "model.language_model.layers.11.mlp.shared_expert_gate",
+      "model.language_model.layers.12.mlp.shared_expert_gate",
+      "model.language_model.layers.13.mlp.shared_expert_gate",
+      "model.language_model.layers.14.mlp.shared_expert_gate",
+      "model.language_model.layers.15.mlp.shared_expert_gate",
+      "model.language_model.layers.16.mlp.shared_expert_gate",
+      "model.language_model.layers.17.mlp.shared_expert_gate",
+      "model.language_model.layers.18.mlp.shared_expert_gate",
+      "model.language_model.layers.19.mlp.shared_expert_gate",
+      "model.language_model.layers.20.mlp.shared_expert_gate",
+      "model.language_model.layers.21.mlp.shared_expert_gate",
+      "model.language_model.layers.22.mlp.shared_expert_gate",
+      "model.language_model.layers.23.mlp.shared_expert_gate",
+      "model.language_model.layers.24.mlp.shared_expert_gate",
+      "model.language_model.layers.25.mlp.shared_expert_gate",
+      "model.language_model.layers.26.mlp.shared_expert_gate",
+      "model.language_model.layers.27.mlp.shared_expert_gate",
+      "model.language_model.layers.28.mlp.shared_expert_gate",
+      "model.language_model.layers.29.mlp.shared_expert_gate",
+      "model.language_model.layers.30.mlp.shared_expert_gate",
+      "model.language_model.layers.31.mlp.shared_expert_gate",
+      "model.language_model.layers.32.mlp.shared_expert_gate",
+      "model.language_model.layers.33.mlp.shared_expert_gate",
+      "model.language_model.layers.34.mlp.shared_expert_gate",
+      "model.language_model.layers.35.mlp.shared_expert_gate",
+      "model.language_model.layers.36.mlp.shared_expert_gate",
+      "model.language_model.layers.37.mlp.shared_expert_gate",
+      "model.language_model.layers.38.mlp.shared_expert_gate",
+      "model.language_model.layers.39.mlp.shared_expert_gate",
+      "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,
+    "attn_output_gate": true,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_moe_text",
+    "moe_intermediate_size": 512,
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_experts": 256,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 2,
+    "output_router_logits": false,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "router_aux_loss_coef": 0.001,
+    "shared_expert_intermediate_size": 512,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.4",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_moe",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 248044,
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.5.4"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88ef720d2494696e810836403b71058edae003354c8e4f96f7b81ca33a2f6cb
+size 5369246576

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa2512e707804425bd365c5aabfa0cc125fdff05b490269700a9a2548660573
+size 5369957608

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f42ed75c9a95c8b61be6149039c4572f687fc3894818e3f2a659dbf4ed7381
+size 5369674984

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d877d9ce33103cd6274cdd52517f21aa63aa01e5fb0494cb0834c2ef9d4ad6
+size 5369804192

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cc18c2cbc4ef3a0244c7e420c103395be9eba24846ad08953c351b1e36334f
+size 5369638224

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7c1f0d3f94bee734a3ee2c3cd6bce2a93b81b6c62b8c579ed2b590e32539c9
+size 5369789704

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791092c656fb64c4e8f2d00a179ea9c47236a961c1cef80130420960987c0b63
+size 4447789320

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}