initial release

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+ukisai-banner.png filter=lfs diff=lfs merge=lfs -text
+swift-speed-demo.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,328 @@
+---
+base_model: ukisai/Swift-Qwen3.8-27b
+library_name: transformers
+license: other
+license_name: swift-open-license-1.0
+pipeline_tag: image-text-to-text
+tags:
+- qwen3_8
+- efficient-thinking
+- reasoning
+- token-efficient
+- amd
+- rocm
+- int4
+- awq
+- quark
+- w4a16
+base_model_relation: quantized
+---
+
+<div align="center">
+  <a href="https://ukisai.com"><img src="ukisai-banner.png" alt="UkisAI" style="width:100%;max-width:100%;height:auto;display:block;margin-bottom:0.6em;" /></a>
+  <div style="display:flex;justify-content:center;gap:0.6em;margin-bottom:1em;">
+    <a href="https://ukisai.com"><strong>Website</strong></a> &nbsp;&bull;&nbsp;
+    <a href="https://ukisai.com/products/swift"><strong>Learn more</strong></a> &nbsp;&bull;&nbsp;
+    <a href="https://huggingface.co/ukisai/Swift-Qwen3.8-27B-GGUF"><strong>GGUF</strong></a> &nbsp;&bull;&nbsp;
+    <a href="#license-and-access"><strong>Enterprise licensing</strong></a>
+  </div>
+</div>
+
+# Swift-Qwen3.8-27b-int4-AMD
+
+AMD Quark AWQ INT4 (W4A16) edition of Swift. The following introduction describes the base Swift results; release-specific details are below.
+
+Swift-Qwen3.8-27B is UkisAI's reasoning-efficient derivative of Qwen3.8-27B,
+using **58.3% fewer thinking tokens** while maintaining near-identical performance
+(**&lt;1% loss**) and as a result getting a **x1.95 speed-up** on several tasks.
+
+<video controls autoplay muted loop playsinline style="width:100%;max-width:100%;height:auto;display:block;border-radius:12px;margin:0.8em 0 1.4em;" src="https://huggingface.co/ukisai/Swift-Qwen3.8-27b-int4-AMD/resolve/main/swift-speed-demo.mp4"></video>
+<p align="center" style="font-size:13px;color:#8C94A8;margin:-0.6em 0 1.4em;">The prompt is a sample from LiveCodeBench v6</p>
+
+## AMD Quark INT4 release
+
+This is the **INT4 W4A16 quantization of Swift for AMD hardware workflows**, produced
+with [AMD Quark](https://github.com/amd/Quark). It uses Quark's **PyTorch** workflow
+and native Hugging Face safetensors export: signed symmetric INT4 weights,
+groups of 128, and BF16 activations.
+
+The full-precision companion is
+[Swift-Qwen3.8-27b-BF16-AMD](https://huggingface.co/ukisai/Swift-Qwen3.8-27b-BF16-AMD).
+
+| Property | This checkpoint |
+| --- | --- |
+| Source | [Swift-Qwen3.8-27B](https://huggingface.co/ukisai/Swift-Qwen3.8-27b) |
+| Quantizer | AMD Quark AWQ |
+| Weight / activation precision | INT4 / BF16 (W4A16) |
+| Weight grouping | Symmetric, group size 128 |
+| Format | Native Quark safetensors, `real_quantized`, `reorder` packing |
+| Weight files | 19.513 GB; BF16 source: 55.563 GB |
+| Calibration | 128 Pile validation samples, 512 tokens each |
+| Quantized layers | 496 eligible language-model linear layers |
+| Preserved components | BF16 vision tower, output head, embeddings, and all 15 MTP tensors |
+
+Quark supports preparing models for AMD deployment. **This checkpoint was quantized
+and validated on an NVIDIA H100; AMD/ROCm serving and throughput have not yet been
+validated.** Serving needs a runtime that supports this native Quark INT4 format.
+The [Quark project](https://github.com/amd/Quark) and
+[installation guide](https://quark.docs.amd.com/latest/install.html) describe its
+supported CUDA and ROCm environments.
+
+### Checkpoint validation
+
+| Sanity check | BF16 | This INT4 export |
+| --- | ---: | ---: |
+| Wikitext perplexity | 9.16197 | 9.54254 |
+| Arithmetic generation | Pass | Pass |
+| JSON generation | Pass | Pass |
+
+Perplexity uses the same eight non-overlapping 512-token Wikitext-2 test windows.
+The 4.15% perplexity increase is a small sanity result, not a full accuracy benchmark.
+The packed checkpoint was independently reloaded, including its final configuration
+and index, and reproduced the evaluation NLLs exactly. All floating tensors are
+finite; 349 preserved vision/output-head/MTP tensors match the source exactly.
+Vision inference and MTP decoding were not exercised in this validation.
+See [quantization_report.json](quantization_report.json).
+
+**The Swift benchmarks and speed demonstration below are reproduced from the base
+Swift model card. They do not measure this Quark export or AMD hardware.**
+
+## Training approach
+
+We built Swift by identifying reasoning-marker tokens that, in our analysis, trigger overthinking in Qwen’s
+reasoning rollouts. We then fine-tuned Qwen by penalizing usage of those tokens while it reasons.
+
+Swift produces shorter reasoning traces. In our testing, we also observe fewer overthinking errors.
+
+For maximum gains, Swift also includes a transfer component derived from
+[BottleCap AI's ThinkingCap-Qwen3.6-27B](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.6-27B).
+
+## Evaluation scope
+
+> All results below compare the Qwen3.8-27B BF16 base with the same base plus the
+> Swift adapter.
+
+## Benchmarks
+
+<style>
+.swift-table { width:100%; table-layout:fixed; border-collapse:separate; border-spacing:0; overflow:hidden; border:1px solid #27344A; border-radius:20px; background:#0D111B; font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,sans-serif; font-size:14px; color:#BFBDBD; }
+.swift-table th { padding:13px 8px; text-align:center; font-weight:700; color:#AEB5C7; background:#0D111B; border-right:1px solid #27344A; border-bottom:1px solid #27344A; }
+.swift-table td { padding:14px 8px; text-align:center; color:#BFBDBD; background:#0D111B; border-right:1px solid #27344A; border-bottom:1px solid #27344A; vertical-align:middle; overflow-wrap:break-word; }
+.swift-table tr > :last-child { border-right:0; }
+.swift-table tbody tr:last-child td { border-bottom:0; }
+.swift-table .benchmark-heading { color:#B7BDCD; background:#0D111B; border-bottom:3px solid #7D45B5; }
+.swift-table .score-heading { color:#F0C5FF; background:#52239E; border-bottom:3px solid #7D45B5; }
+.swift-table .tokens-heading, .swift-table .median-heading { color:#D4E8FF; background:#304FC2; border-bottom:3px solid #5687E6; }
+.swift-table .benchmark { padding-left:18px; text-align:left; color:#FFFFFF; font-weight:600; }
+.swift-table strong { color:#FFFFFF; }
+.swift-table .section { padding:12px 18px; text-align:left; color:#B489FF; background:#2A2541; font-weight:700; letter-spacing:.08em; text-transform:uppercase; border-top:1px solid #3A3159; border-bottom:1px solid #3A3159; }
+.swift-table .swift { background:#171127; }
+.swift-table thead tr:nth-child(2) .swift { color:#D3A0FF; }
+.swift-table .reduction { color:#69BFFF; background:#101B2C; font-weight:700; }
+.swift-table .detail { color:#8C94A8; font-size:12px; font-weight:500; }
+
+@media (max-width: 640px) {
+  .swift-table { display:block !important; width:100% !important; max-width:100%; overflow-x:auto !important; -webkit-overflow-scrolling:touch; table-layout:auto !important; }
+  .swift-table th, .swift-table td { min-width:100px; }
+  .swift-table th:first-child, .swift-table td:first-child { min-width:160px; }
+}
+</style>
+
+<table class="swift-table">
+  <thead>
+    <tr>
+      <th rowspan="2" class="benchmark-heading" style="width:32%;text-align:left;padding-left:18px;vertical-align:bottom;">Benchmark</th>
+      <th colspan="2" class="score-heading">Score</th>
+      <th colspan="3" class="tokens-heading">Mean tokens</th>
+      <th class="median-heading" style="width:14%;">Median tokens</th>
+    </tr>
+    <tr>
+      <th>Base</th>
+      <th class="swift">Swift</th>
+      <th>Base</th>
+      <th class="swift">Swift</th>
+      <th class="reduction">Reduction</th>
+      <th class="reduction">Reduction</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr><td class="section" colspan="7">General reasoning</td></tr>
+    <tr><td class="benchmark">GPQA-Diamond</td><td>88.38%</td><td class="swift">88.28%</td><td>15,014</td><td class="swift"><strong>8,855</strong></td><td class="reduction">&darr; 41.0%</td><td class="reduction">&darr; 58.3%</td></tr>
+    <tr><td class="benchmark">MMLU-Pro</td><td>85.47%</td><td class="swift">84.95%</td><td>2,980</td><td class="swift"><strong>1,603</strong></td><td class="reduction">&darr; 46.2%</td><td class="reduction">&darr; 28.3%</td></tr>
+    <tr><td class="benchmark">C-Eval</td><td>90.00%</td><td class="swift">90.62%</td><td>1,492</td><td class="swift"><strong>804</strong></td><td class="reduction">&darr; 46.1%</td><td class="reduction">&darr; 19.3%</td></tr>
+    <tr><td class="benchmark">IFBench</td><td>73.53%</td><td class="swift">71.80%</td><td>8,052</td><td class="swift"><strong>4,657</strong></td><td class="reduction">&darr; 42.2%</td><td class="reduction">&darr; 50.5%</td></tr>
+    <tr><td class="section" colspan="7">Mathematics</td></tr>
+    <tr><td class="benchmark">AIME 2026</td><td>98.67%</td><td class="swift">94.00%</td><td>22,014</td><td class="swift"><strong>16,143</strong></td><td class="reduction">&darr; 26.7%</td><td class="reduction">&darr; 50.2%</td></tr>
+    <tr><td class="benchmark">HMMT (Nov 2025)</td><td>99.33%</td><td class="swift">96.00%</td><td>22,032</td><td class="swift"><strong>15,189</strong></td><td class="reduction">&darr; 31.1%</td><td class="reduction">&darr; 45.9%</td></tr>
+    <tr><td class="section" colspan="7">Multimodal</td></tr>
+    <tr><td class="benchmark">ERQA</td><td>67.45%</td><td class="swift">66.30%</td><td>4,137</td><td class="swift"><strong>2,045</strong></td><td class="reduction">&darr; 50.6%</td><td class="reduction">&darr; 54.6%</td></tr>
+    <tr><td class="section" colspan="7">Agentic coding</td></tr>
+    <tr><td class="benchmark">Terminal-Bench 2.1</td><td>66.74%</td><td class="swift">65.84%</td><td>37,086</td><td class="swift"><strong>27,272</strong></td><td class="reduction">&darr; 26.5%</td><td class="reduction">&darr; 38.7%</td></tr>
+    <tr><td class="benchmark">LiveCodeBench v6</td><td>76.76%</td><td class="swift">81.55%</td><td>11,374</td><td class="swift"><strong>8,615</strong></td><td class="reduction">&darr; 24.3%</td><td class="reduction">&darr; 45.8%</td></tr>
+  </tbody>
+</table>
+
+<details>
+<summary><strong>How to reproduce</strong></summary>
+
+<p style="font-size:13px;line-height:1.5;margin:8px 0;"><strong>Serving:</strong> BF16 · vLLM 0.27.1 · Qwen3 parser · context 262,144 · thinking xhigh.<br>
+<strong>Sampling:</strong> temperature 1.0 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 0 · repetition_penalty 1.<br>
+<strong>Benchmarks:</strong> averages over five seeds (0–4) per model; five trials per task for Terminal-Bench.</p>
+
+<table style="display:table;width:100%;border-collapse:collapse;font-size:13px;line-height:1.3;margin:8px 0;">
+  <thead><tr><th style="padding:4px 8px;text-align:left;">Benchmark</th><th style="padding:4px 8px;text-align:right;">Output cap</th></tr></thead>
+  <tbody>
+    <tr><td style="padding:3px 8px;">GPQA-Diamond</td><td style="padding:3px 8px;text-align:right;">100,000</td></tr>
+    <tr><td style="padding:3px 8px;">MMLU-Pro</td><td style="padding:3px 8px;text-align:right;">100,000</td></tr>
+    <tr><td style="padding:3px 8px;">C-Eval</td><td style="padding:3px 8px;text-align:right;">16,384</td></tr>
+    <tr><td style="padding:3px 8px;">IFBench</td><td style="padding:3px 8px;text-align:right;">81,920</td></tr>
+    <tr><td style="padding:3px 8px;">AIME 2026</td><td style="padding:3px 8px;text-align:right;">250,000</td></tr>
+    <tr><td style="padding:3px 8px;">HMMT Nov 2025</td><td style="padding:3px 8px;text-align:right;">250,000</td></tr>
+    <tr><td style="padding:3px 8px;">ERQA</td><td style="padding:3px 8px;text-align:right;">100,000</td></tr>
+    <tr><td style="padding:3px 8px;">Terminal-Bench 2.1</td><td style="padding:3px 8px;text-align:right;">Agent/task limits</td></tr>
+    <tr><td style="padding:3px 8px;">LiveCodeBench v6</td><td style="padding:3px 8px;text-align:right;">32,768</td></tr>
+  </tbody>
+</table>
+
+</details>
+
+## Efficiency across and versus reasoning efforts
+
+Qwen3.8's `reasoning_effort` setting lets users choose how much the model thinks.
+For Swift to be useful across these settings, it needs to reduce thinking while
+keeping accuracy close to the base. We therefore tested `xhigh`, `medium`, and `low`:
+thinking-token savings persist at every level.
+
+<table class="swift-table" style="display:table;width:100%;table-layout:fixed;">
+  <thead>
+    <tr>
+      <th class="benchmark-heading" style="width:50%;text-align:left;padding-left:18px;white-space:normal;">Reasoning effort</th>
+      <th class="tokens-heading" style="width:50%;white-space:normal;">Mean thinking reduction</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr><td class="benchmark">Xhigh</td><td class="reduction">&darr; 41.0%</td></tr>
+    <tr><td class="benchmark">Medium</td><td class="reduction">&darr; 22.7%</td></tr>
+    <tr><td class="benchmark">Low</td><td class="reduction">&darr; 25.8%</td></tr>
+  </tbody>
+</table>
+
+The efficiency also holds up against the base's own lower effort settings. On
+GPQA-Diamond (198 questions, 5 seeds, 990 paired calls), Swift at `xhigh` is
+compared with the base at `xhigh` and at `medium`:
+
+<table class="swift-table" style="display:table;width:100%;table-layout:fixed;">
+  <thead>
+    <tr>
+      <th class="benchmark-heading" style="width:34%;text-align:left;padding-left:18px;white-space:normal;">GPQA-Diamond</th>
+      <th class="score-heading" style="width:22%;white-space:normal;">Score</th>
+      <th class="tokens-heading" style="width:22%;white-space:normal;">Mean tokens</th>
+      <th class="median-heading" style="width:22%;white-space:normal;">Median tokens</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr><td class="benchmark">Base &middot; xhigh</td><td>88.38%</td><td>15,014</td><td>6,642</td></tr>
+    <tr class="swift"><td class="benchmark swift">Swift &middot; xhigh</td><td class="swift"><strong>88.28%</strong></td><td class="swift"><strong>8,855</strong></td><td class="swift"><strong>2,771</strong></td></tr>
+    <tr><td class="benchmark">Base &middot; medium</td><td>84.14%</td><td>4,451</td><td>1,753</td></tr>
+  </tbody>
+</table>
+
+Swift retains the accuracy of `xhigh` while using about half the tokens, although
+it uses about double the tokens of `medium`.
+
+## Quantized models
+
+Quantized deployment is the intended use for Swift: lower-memory weights paired with
+shorter reasoning. The INT4 evaluations below retain token savings across GPQA,
+IFBench, and AIME. On AIME, Swift matches or improves accuracy and reduces output-cap
+failures by **31–33%**.
+
+<table class="swift-table" style="display:table;width:100%;table-layout:fixed;">
+  <thead><tr>
+    <th class="benchmark-heading" style="width:32%;text-align:left;padding-left:18px;white-space:normal;">Benchmark / quantization</th>
+    <th class="score-heading" style="width:16%;white-space:normal;">Base accuracy</th>
+    <th class="score-heading" style="width:16%;white-space:normal;">Swift accuracy</th>
+    <th class="tokens-heading" style="width:18%;white-space:normal;">Mean token reduction</th>
+    <th class="median-heading" style="width:18%;white-space:normal;">Median token reduction</th>
+  </tr></thead>
+  <tbody>
+    <tr><td class="benchmark">GPQA-Diamond<br><span class="detail">Mixed-precision quant W4A16 · thinking tokens</span></td><td>88.69%</td><td class="swift">88.38%</td><td class="reduction">&darr; 32.1%</td><td class="reduction">&darr; 50.2%</td></tr>
+    <tr><td class="benchmark">IFBench<br><span class="detail">Mixed-precision quant W4A16 · completion tokens</span></td><td>72.58%</td><td class="swift">71.25%</td><td class="reduction">&darr; 30.1%</td><td class="reduction">&darr; 38.0%</td></tr>
+    <tr><td class="benchmark">AIME 2026<br><span class="detail">Mixed-precision quant W4A16 · completion tokens</span></td><td>84.00%</td><td class="swift">84.00%</td><td class="reduction">&darr; 19.0%</td><td class="reduction">&darr; 37.5%</td></tr>
+    <tr><td class="benchmark">AIME 2026<br><span class="detail">AWQ INT4 · completion tokens</span></td><td>82.67%</td><td class="swift">84.00%</td><td class="reduction">&darr; 22.8%</td><td class="reduction">&darr; 34.8%</td></tr>
+  </tbody>
+</table>
+
+<details>
+<summary><strong>Quantized evaluation settings</strong></summary>
+
+Each row compares the same quantized base with and without the Swift adapter.
+GPQA and AIME use five seeds; IFBench uses four samples per prompt and strict scoring.
+Output caps: GPQA 100,000; IFBench 81,920; AIME 32,768. GPQA and IFBench use saved
+historical base runs. AIME uses template-default effort and counts truncated answers
+as incorrect. Its shorter cap makes it a separate comparison from the BF16 table.
+
+</details>
+
+## How to use
+
+### PyTorch with AMD Quark
+
+Install the GPU-specific PyTorch and Quark packages from the
+[official installation guide](https://quark.docs.amd.com/latest/install.html).
+Validation used Python 3.12, PyTorch 2.11.0+cu128, Transformers 5.2.0,
+AMD Quark 0.12.post1+cu128.torch2.11, Accelerate 1.15.0, and Safetensors 0.8.0.
+For AMD, select the corresponding supported ROCm environment.
+
+Download this repository and run the included loader:
+
+```bash
+hf download ukisai/Swift-Qwen3.8-27b-int4-AMD --local-dir Swift-Qwen3.8-27b-int4-AMD
+python Swift-Qwen3.8-27b-int4-AMD/load_quark.py \
+  --model Swift-Qwen3.8-27b-int4-AMD \
+  --prompt "What is 17 multiplied by 23? Answer with only the number."
+```
+
+[`load_quark.py`](load_quark.py) imports the packed weights through Quark's PyTorch
+API. The included [`quark_compat.py`](quark_compat.py) handles the public Quark
+0.12 dense-Qwen reload path. The model uses the `qwen3_5` Transformers architecture
+identifier. [`recipe.py`](recipe.py) records the AWQ configuration.
+The example disables thinking for a short deterministic smoke check.
+
+### Serving
+
+A serving engine must support native Quark W4A16 signed INT4 with `reorder` packing
+and this Qwen architecture. As of September 14, 2026,
+[vLLM's native Quark INT4 support PR](https://github.com/vllm-project/vllm/pull/48606)
+remains open. Stock vLLM compatibility and AMD performance are not established by
+the PyTorch validation above. The preserved MTP head also needs compatible runtime
+support before speculative decoding can be used.
+
+For standard BF16 serving instructions, see the
+[BF16 companion](https://huggingface.co/ukisai/Swift-Qwen3.8-27b-BF16-AMD).
+The [base Swift card](https://huggingface.co/ukisai/Swift-Qwen3.8-27b#how-to-use) also documents the
+UkisAI API and other Swift formats; that API is separate from this downloadable
+Quark checkpoint.
+
+## License and access
+
+Swift weights are distributed under the **Swift Open License v1.0**.
+Personal, research, educational, evaluation, and commercial use are free for individuals
+and organizations with annual recurring revenue, including affiliates, of up to
+US$1,000,000. Above that threshold, commercial use requires a separate **Swift Enterprise
+License**. Contact [UkisAI](https://ukisai.com/contact) for terms.
+
+## Citation
+
+```bibtex
+@misc{swift-qwen3.8-27b,
+  title  = {Swift-Qwen3.8-27B},
+  author = {UkisAI},
+  year   = {2026},
+  url    = {https://huggingface.co/ukisai/Swift-Qwen3.8-27b}
+}
+```
+
+## Acknowledgements
+
+We acknowledge the [NVIDIA Innovation Lab](https://www.nvidia.com/en-us/data-center/innovation-lab/) for providing access to **8× NVIDIA H100 GPUs** to train Swift.

SHA256SUMS

@@ -0,0 +1,17 @@
+ee88be55447e3bfb8aef842fd7eb4819c75578189d3ecc86c3f0032dbac97422  README.md
+c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041  chat_template.jinja
+fbc21d89ddaa82af0b79d3ccd328a76b863f36d4190b8c4a0100a29faf853d89  config.json
+e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e  generation_config.json
+86a714fcfc05b610e2d664b0d8385ad5a38421e9370712096194efd9e72dd8b1  load_quark.py
+a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d  merges.txt
+0f4e5cb71a806ff2ced530144b243d3ab28ca7068d41d89f5e42aa609d6f99db  model.safetensors.index.json
+27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516  preprocessor_config.json
+73f2751bc256b5f4ffc7df65b1a1cf201b27dbcb3024677e9d0f470b20e7fa3a  quantization_report.json
+28333acab30e77ba4801a32682251830a7a26dfe490f67999e26de3b6987463a  quark_compat.py
+5d8f0744f0b4aab61ca58c03fc83698072cdf5f2d149880871021b0babb94dbc  recipe.py
+0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3  tokenizer.json
+b11349aafa7cdc6a320767cf7ceb29ed82f7eda5d65e8e0819e76f0ce947bf27  tokenizer_config.json
+3e9e39451b4586f86a8c7c12dfbba21a5adc16778543d93e39b139ca8627f0c7  ukisai-banner.png
+7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13  video_preprocessor_config.json
+ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003  vocab.json
+a792a58dcc5b8f5b663f81c3f5024e0bc7cccc5290e2254e006f2845fdd5c247  model.safetensors

chat_template.jinja

@@ -0,0 +1,170 @@
+{%- 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 %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# 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 %}
+        {%- if content %}
+            {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + content + '<|im_end|>\n' }}
+        {%- elif reasoning_instructions %}
+            {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+        {%- endif %}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|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 %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or 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 and tool_call.arguments != '' %}
+                    {%- 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 +1,335 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen3_5",
+  "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": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "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_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": 48,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 4,
+    "output_gate_type": "swish",
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0.dev0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "quantization_config": {
+    "algo_config": [
+      {
+        "model_decoder_layers": "model.language_model.layers",
+        "name": "awq",
+        "scaling_layers": [
+          {
+            "inp": "mlp.gate_proj",
+            "layers": [
+              "mlp.gate_proj",
+              "mlp.up_proj"
+            ],
+            "module2inspect": "mlp",
+            "prev_op": "post_attention_layernorm"
+          },
+          {
+            "inp": "mlp.down_proj",
+            "layers": [
+              "mlp.down_proj"
+            ],
+            "prev_op": "mlp.up_proj"
+          }
+        ]
+      }
+    ],
+    "exclude": [
+      "lm_head",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.visual.pos_embed",
+      "mtp.*",
+      "mtp.fc.weight",
+      "mtp.layers.0.input_layernorm.weight",
+      "mtp.layers.0.mlp.down_proj.weight",
+      "mtp.layers.0.mlp.gate_proj.weight",
+      "mtp.layers.0.mlp.up_proj.weight",
+      "mtp.layers.0.post_attention_layernorm.weight",
+      "mtp.layers.0.self_attn.k_norm.weight",
+      "mtp.layers.0.self_attn.k_proj.weight",
+      "mtp.layers.0.self_attn.o_proj.weight",
+      "mtp.layers.0.self_attn.q_norm.weight",
+      "mtp.layers.0.self_attn.q_proj.weight",
+      "mtp.layers.0.self_attn.v_proj.weight",
+      "mtp.norm.weight",
+      "mtp.pre_fc_norm_embedding.weight",
+      "mtp.pre_fc_norm_hidden.weight"
+    ],
+    "export": {
+      "kv_cache_group": [],
+      "min_kv_scale": 0.0,
+      "pack_method": "reorder",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "global_quant_config": {
+      "bias": null,
+      "input_tensors": null,
+      "output_tensors": null,
+      "target_device": null,
+      "weight": {
+        "block_size": null,
+        "ch_axis": -1,
+        "dtype": "int4",
+        "enable_buffer_reuse": false,
+        "group_size": 128,
+        "is_dynamic": false,
+        "is_scale_quant": false,
+        "max_input_numel": 4194304,
+        "mx_element_dtype": null,
+        "observer_cls": "PerGroupMinMaxObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "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": "0.12.post1+cu128.torch2.11"
+  }
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "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
+}

load_quark.py

@@ -0,0 +1,48 @@
+"""Load Swift's native Quark INT4 checkpoint for PyTorch inference."""
+import argparse
+from pathlib import Path
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--model", default="ukisai/Swift-Qwen3.8-27b-int4-AMD")
+    parser.add_argument("--prompt", default="What is 17 multiplied by 23? Answer with only the number.")
+    parser.add_argument("--max-new-tokens", type=int, default=128)
+    parser.add_argument("--device", default="cuda:0")
+    args = parser.parse_args()
+
+    import torch
+    from accelerate import init_empty_weights
+    from huggingface_hub import snapshot_download
+    from transformers import AutoConfig, AutoTokenizer, GenerationConfig, Qwen3_5ForConditionalGeneration
+    from transformers.initialization import no_init_weights
+    from quark.torch import import_model_from_safetensors
+    from quark_compat import dense_qwen_reload_support
+
+    checkpoint = args.model if Path(args.model).is_dir() else snapshot_download(
+        args.model, allow_patterns=["*.safetensors", "*.json", "*.jinja", "*.txt"]
+    )
+    config = AutoConfig.from_pretrained(checkpoint)
+    config._attn_implementation = "eager"
+    with no_init_weights(), init_empty_weights():
+        model = Qwen3_5ForConditionalGeneration(config)
+    with dense_qwen_reload_support():
+        model = import_model_from_safetensors(model, checkpoint, device="cpu")
+    model.generation_config = GenerationConfig.from_pretrained(checkpoint)
+    model.to(args.device).eval()
+    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+    inputs = tokenizer.apply_chat_template(
+        [{"role": "user", "content": args.prompt}],
+        tokenize=True, add_generation_prompt=True, enable_thinking=False,
+        return_tensors="pt", return_dict=True,
+    ).to(args.device)
+    with torch.inference_mode():
+        outputs = model.generate(
+            **inputs, max_new_tokens=args.max_new_tokens, do_sample=False,
+            use_cache=True, pad_token_id=tokenizer.eos_token_id,
+        )
+    print(tokenizer.decode(outputs[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+
+
+if __name__ == "__main__":
+    main()

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a792a58dcc5b8f5b663f81c3f5024e0bc7cccc5290e2254e006f2845fdd5c247
+size 19512909752

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"
+}

quantization_report.json

@@ -0,0 +1,114 @@
+{
+  "source_model": "ukisai/Swift-Qwen3.8-27b",
+  "source_revision": "1b30aaaf753fe5c1cb51ada2ea0367a53445359c",
+  "checkpoint": "ukisai/Swift-Qwen3.8-27b-int4-AMD",
+  "framework": "PyTorch",
+  "validation_hardware": "NVIDIA H100",
+  "amd_hardware_tested": false,
+  "versions": {
+    "torch": "2.11.0+cu128",
+    "transformers": "5.2.0",
+    "amd-quark": "0.12.post1+cu128.torch2.11",
+    "accelerate": "1.15.0",
+    "safetensors": "0.8.0"
+  },
+  "evaluation_data": {
+    "dataset": "Salesforce/wikitext",
+    "config": "wikitext-2-raw-v1",
+    "split": "test",
+    "fingerprint": "a46124b21ac53738",
+    "windows": 8,
+    "window_length": 512,
+    "selection": "first 4096 tokens; small sanity check, not full benchmark",
+    "input_sha256": "2ebdb31fd4394419aabae16a635375c8e70d306c14462051d849056893cd2b27"
+  },
+  "evaluation": {
+    "label": "int4-final-export",
+    "nlls": [
+      1.820142388343811,
+      2.3994803428649902,
+      2.3420217037200928,
+      2.2320547103881836,
+      2.1242759227752686,
+      2.34279727935791,
+      2.3792335987091064,
+      2.4060728549957275
+    ],
+    "mean_nll": 2.2557598501443863,
+    "perplexity": 9.542541457549426,
+    "samples": [
+      {
+        "prompt": "What is 17 multiplied by 23? Answer with only the number.",
+        "answer": "391",
+        "generated_tokens": 4
+      },
+      {
+        "prompt": "Return only valid JSON with keys \"status\" set to \"ok\" and \"count\" set to 3.",
+        "answer": "{\"status\": \"ok\", \"count\": 3}",
+        "generated_tokens": 13
+      }
+    ],
+    "evaluation_seconds": 49.92316593322903,
+    "scope": "8 non-overlapping 512-token Wikitext test windows; sanity check only"
+  },
+  "quantization": "Quark AWQ signed INT4, symmetric groups of 128, BF16 activations",
+  "calibration": {
+    "dataset": "mit-han-lab/pile-val-backup",
+    "split": "validation",
+    "fingerprint": "fa7b9ce01fad1b22",
+    "samples": 128,
+    "sequence_length": 512,
+    "selection": "first 128 rows, matching AMD's example default",
+    "padding": "left, EOS token, matching Quark get_tokenizer",
+    "input_sha256": "9bbae467c3c633d882fdfad4f398aea0515c211c26eafea482585ddb73995b15"
+  },
+  "audit": {
+    "tensor_bytes": 19512618464,
+    "weight_scale_tensors": 496,
+    "preserved_mtp_tensors": 15,
+    "exact_preserved_tensors": 349,
+    "mtp_tensors_already_exported": 15,
+    "mtp_tensors_added": 0,
+    "copied_file_sha256": {
+      "chat_template.jinja": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041",
+      "generation_config.json": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e",
+      "merges.txt": "a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d",
+      "preprocessor_config.json": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
+      "tokenizer_config.json": "b11349aafa7cdc6a320767cf7ceb29ed82f7eda5d65e8e0819e76f0ce947bf27",
+      "video_preprocessor_config.json": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13",
+      "vocab.json": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003",
+      "tokenizer.json": "0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3"
+    }
+  },
+  "round_trip_max_nll_difference": 0.0,
+  "bf16_reference": {
+    "label": "bf16",
+    "nlls": [
+      1.7963014841079712,
+      2.3732309341430664,
+      2.2346465587615967,
+      2.221674919128418,
+      2.0747108459472656,
+      2.3078770637512207,
+      2.3398988246917725,
+      2.372152090072632
+    ],
+    "mean_nll": 2.215061590075493,
+    "perplexity": 9.161973380864124,
+    "samples": [
+      {
+        "prompt": "What is 17 multiplied by 23? Answer with only the number.",
+        "answer": "391",
+        "generated_tokens": 4
+      },
+      {
+        "prompt": "Return only valid JSON with keys \"status\" set to \"ok\" and \"count\" set to 3.",
+        "answer": "{\"status\": \"ok\", \"count\": 3}",
+        "generated_tokens": 13
+      }
+    ],
+    "evaluation_seconds": 6.864971877075732,
+    "scope": "8 non-overlapping 512-token Wikitext test windows; sanity check only"
+  },
+  "perplexity_ratio_int4_over_bf16": 1.041537784586906
+}

quark_compat.py

@@ -0,0 +1,31 @@
+"""Process-local compatibility for dense Qwen3.5/3.8 in Quark 0.12.
+
+Quark's reload path invokes its MoE preparation helper even for dense models.
+That helper explicitly rejects qwen3_5. Dense Qwen needs no expert conversion;
+all quantized modules are ordinary Linear layers. Keep every other architecture
+on the original path and restore the helper after each import.
+"""
+from contextlib import contextmanager
+
+
+@contextmanager
+def dense_qwen_reload_support():
+    from quark.torch.utils.llm import model_preparation
+
+    original = model_preparation._prepare_for_moe_quant
+
+    def prepare(model, reload=False):
+        if getattr(model.config, "model_type", None) == "qwen3_5":
+            text_config = model.config.text_config
+            if getattr(text_config, "num_experts", 0):
+                raise ValueError("This compatibility path only supports dense Qwen")
+            if any("expert" in type(module).__name__.lower() for module in model.modules()):
+                raise ValueError("Unexpected expert module in dense Qwen")
+            return
+        return original(model, reload)
+
+    model_preparation._prepare_for_moe_quant = prepare
+    try:
+        yield
+    finally:
+        model_preparation._prepare_for_moe_quant = original

recipe.py

@@ -0,0 +1,34 @@
+"""Quark recipe matching AMD's published Qwen3.8-27B AWQ configuration."""
+from quark.torch.quantization.config.config import (
+    AWQConfig,
+    Int4PerGroupSpec,
+    QConfig,
+    QLayerConfig,
+)
+
+
+def make_config():
+    return QConfig(
+        global_quant_config=QLayerConfig(
+            weight=Int4PerGroupSpec(ch_axis=-1, group_size=128).to_quantization_spec()
+        ),
+        exclude=["model.visual.*", "lm_head", "mtp.*"],
+        algo_config=[
+            AWQConfig(
+                model_decoder_layers="model.language_model.layers",
+                scaling_layers=[
+                    {
+                        "prev_op": "post_attention_layernorm",
+                        "layers": ["mlp.gate_proj", "mlp.up_proj"],
+                        "inp": "mlp.gate_proj",
+                        "module2inspect": "mlp",
+                    },
+                    {
+                        "prev_op": "mlp.up_proj",
+                        "layers": ["mlp.down_proj"],
+                        "inp": "mlp.down_proj",
+                    },
+                ],
+            )
+        ],
+    )

swift-speed-demo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdc350da93f0f957d47674d62cf1308e9288d40790243045d95d1f88ae6eb79
+size 7505194

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
+size 12809320

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "additional_special_tokens": [
+        "<|im_start|>",
+        "<|im_end|>",
+        "<|object_ref_start|>",
+        "<|object_ref_end|>",
+        "<|box_start|>",
+        "<|box_end|>",
+        "<|quad_start|>",
+        "<|quad_end|>",
+        "<|vision_start|>",
+        "<|vision_end|>",
+        "<|vision_pad|>",
+        "<|image_pad|>",
+        "<|video_pad|>"
+    ],
+    "bos_token": null,
+    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set reasoning_instructions = '' %}\n{%- if enable_thinking is undefined or enable_thinking is true %}\n    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}\n    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}\n        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}\n    {%- endif %}\n    {%- if resolved_reasoning_effort == 'xhigh' %}\n        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}\n    {%- elif resolved_reasoning_effort == 'low' %}\n        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}\n    {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if reasoning_instructions %}\n        {{- reasoning_instructions + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\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>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '<|im_start|>system\\n' + (reasoning_instructions + '\\n\\n' if reasoning_instructions else '')  + content + '<|im_end|>\\n' }}\n        {%- elif reasoning_instructions %}\n            {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- elif reasoning_instructions %}\n        {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined and tool_call.arguments != '' %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "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+",
+    "extra_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|>"
+    }
+}

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"
+}