D3-Turbo-NPU2 for FastFlowLM

.gitattributes

@@ -33,3 +33,6 @@ 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
+model.q4nx filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+vision_weight.q4nx filter=lfs diff=lfs merge=lfs -text

LICENSE

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

MANIFEST.sha256

@@ -0,0 +1,11 @@
+c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4  LICENSE
+bd98da8168df588cf3937631ffdfaa39197baf64ef8bc0e0e29685dbab021640  NOTICE
+26398b1c14d979b87142a4d7255d133785d1153fa929ad111d8d832538896a9d  README.md
+c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041  chat_template.jinja
+6f3e928d3292373acb295b0c25a91b4ccb1823ec5e054089075a32617aa2e5c2  config.json
+defc878d6cc6d8535a0198d6e26c11fa904c2ae47297ddf4412a3d2dcd67e81e  decision_config.json
+bb175d0ba981a2581242a8f279003306ec7decd9cc667178f755e2bab2558288  model.q4nx
+f2579067a488138e2ef00bb3e98989cac7311afbf48700dfad02244e3671f241  readout.safetensors
+0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3  tokenizer.json
+b11349aafa7cdc6a320767cf7ceb29ed82f7eda5d65e8e0819e76f0ce947bf27  tokenizer_config.json
+40b02b19596ebd66995bca905ecf481f994183e391505a89204caf965fe69425  vision_weight.q4nx

NOTICE

@@ -0,0 +1,6 @@
+d3-turbo (Decision 3.0)
+Copyright 2026 vLLM Semantic Router Team
+
+Built on Qwen/Qwen3.5-27B (Apache-2.0).
+
+Modified by the FastFlowLM team: weights quantized to the Q4NX format (Q4_K projections, Q8_0 token embedding) for AMD NPUs and repackaged for FastFlowLM. The readout, decision config, tokenizer and chat template are unmodified.

README.md

@@ -0,0 +1,209 @@
+---
+license: apache-2.0
+base_model: vllm-sr/d3-turbo
+pipeline_tag: zero-shot-classification
+tags:
+- decision-model
+- system-one
+- fastflowlm
+- amd-npu
+- q4nx
+---
+
+# D3-Turbo-NPU2
+
+[vllm-sr/d3-turbo](https://huggingface.co/vllm-sr/d3-turbo) `v1.1` (`689b3af1`; Decision 3.0, the 27B multimodal decision
+model of vLLM Semantic Router, Qwen3.5-27B text tower) for AMD Ryzen AI NPUs, served by
+[FastFlowLM](https://github.com/ROCm/FastFlowLM) 1.0.11+.
+It answers *System One* requests -- choice, yes / no and score questions about a state, optionally with images and videos,
+with a probability for every option; `box` questions (where is it in an image or a video) and `track` questions (a box per
+moment over a whole video) as well -- over the same `POST /v1/systemone` API as the upstream package. Up to 32,768 input
+tokens per question. Like upstream d3-turbo it reads the state once per request and answers every question on it
+("ask once, answer many"), so many questions about one input cost far less than one request per question.
+
+```shell
+flm pull d3:turbo                     # 16.6 GB download
+flm serve --decision d3:turbo         # optionally next to a chat model: flm serve qwen3.5:9b --decision d3:turbo
+curl -s http://127.0.0.1:52625/v1/systemone -H "Content-Type: application/json" \
+  -d '{"state": "The order arrived damaged.", "questions": {"route": {"type": "choice",
+       "criteria": {"returns": "Refunds and replacements", "billing": "Payments", "general": null}}}}'
+```
+
+Images go in an `images` list of base64 data URLs (PNG, JPEG or WebP; each at most 8 MB and 16 MP, resized to at most
+1.6 MP), shared by every question of the request. `d3:lite` (0.8B), `d3:nano` (2B) and `d3:mini` (4B) are the smaller
+siblings; they answer a single short question in well under a second, d3:turbo needs a few seconds (see Speed).
+
+## What this package supports on the NPU
+
+| Question / input | Status |
+|---|---|
+| `choice`, `noul` (yes / no), `score` on text | supported |
+| the same with images in the state (several images per request) | supported |
+| Maximum length | 32,768 tokens per question (a longer prompt is answered with `max_length_exceeded`; nothing is truncated) |
+| `long_context=True` (upstream: up to 131,072 tokens) | **not supported** (the request is refused with HTTP 422) |
+
+| Question / input | Status |
+|---|---|
+| `box` (where is it in an image; also at a moment of a video with `at`) | supported: one box per question with a calibrated confidence |
+| `assets` (images inside the state, a question's instructions or its options) | supported |
+| videos in the state (2 frames per second, 4 to 32 frames, at most 0.2 MP per frame) | supported; a video is at most 60 s and 16,384 vision tokens per request; decoding mp4 / webm / mkv / mov / gif needs the FFmpeg shared libraries on the machine (without them the request is refused with HTTP 422; frame lists `{"frames": [...]}` always work) |
+| `track` (a box per moment over a whole video, 1 or 2 updates per second) | supported; at most 256 moments per request (`D3_MOMENT_ROWS`) |
+
+`GET /v1/systemone/models` lists exactly what the running build accepts.
+
+## Requirements
+
+- An AMD Ryzen AI processor with an XDNA 2 NPU (this package was tested on a Strix Halo machine), Linux with the XRT
+  stack, FastFlowLM as above.
+- Memory: the package is 16.6 GB on disk and about 17.9 GB resident once loaded. Measured peak resident memory of the
+  server process: 17.4 GB for prompts up to 4k tokens, 22.4 GB at 24k and **25.3 GB at 32,768 tokens**; the FLM catalog
+  reserves a footprint of 26 GB (plus 8.6 GB of locked scratch memory). All numbers are from a 128 GB machine; smaller
+  machines were not tested, plan for a 32 GB or larger system and do not run it next to other large models.
+- Load time about 17 s (page cache warm).
+
+## What was changed
+
+- **Weights:** the Qwen3.5-27B text tower of d3-turbo quantized to FastFlowLM's Q4NX format: every projection Q4_K with
+  GPTQ-calibrated rounding (our own sequential GPTQ over all 64 layers, 400 tensors; calibration: 300 synthetic System
+  One questions of up to 2k tokens with the model's `prefix_bidir` mask, none from the Decision Index), token embedding
+  Q8_0, norms and the Gated DeltaNet `alpha` / `beta` parameters kept in BF16.
+- **Vision tower:** `vision_weight.q4nx` is made from d3-turbo's own vision encoder (27 layers, 1152 wide, 5120 out),
+  which differs from stock Qwen3.5-27B's in every tensor (it was fine-tuned), then quantized to Q4_K. It runs on
+  FastFlowLM's existing vision kernels.
+- **Attention numerics (`prefix_bidir`):** as upstream, the state block attends bidirectionally to itself, each question
+  block attends to the state and to itself, never the other way, and the Gated DeltaNet layers stay causal. The engine
+  runs the state once and the question blocks on its cached keys / values and recurrent state; a question's answer does
+  not depend on the other questions of the request. `usage.input_tokens` counts the state once plus every question block,
+  as upstream.
+- **Unchanged:** `readout.safetensors`, `decision_config.json`, `tokenizer.json`, `tokenizer_config.json`,
+  `chat_template.jinja`, `LICENSE` are the upstream files byte for byte (`MANIFEST.sha256`); `NOTICE` adds the
+  modification statement. Prompts, token ids and answer objects follow the upstream runtime, with one known difference:
+  FastFlowLM tokenizes with the model's own `tokenizer.json`, while upstream's `transformers` tokenizer drops the
+  combining-mark class from its pre-tokenizer, so text with combining marks (for example an emoji variation selector)
+  can have one token more upstream (the token counts differ by one on 3 of 1,480 test prompts).
+
+## Accuracy (against the upstream BF16 model)
+
+All comparisons use the same requests: the upstream runtime in BF16 as the reference (run on an AMD iGPU, the vision
+tower of the image references on the CPU) and this package on the NPU.
+
+| | this package on the NPU | upstream BF16 |
+|---|---|---|
+| Final-norm hidden state vs BF16, cosine (736 text questions, median / minimum) | 0.9990 / 0.981 | -- |
+| Probability error vs BF16 (736 text questions, median / 99th percentile / maximum) | 0.011 / 0.13 / 0.50 | -- |
+| Same top answer as BF16 (736 text questions) | 95.7% | -- |
+| Same, 5 long prompts of 6k to 24k tokens (cosine median) | 5 / 5 (0.9980) | -- |
+| Same, 60 questions with images (cosine median) | 91.7% (0.9941) | -- |
+
+The plain Q4_K quantization of the same model without GPTQ agreed on 91.0% of the text questions (cosine 0.9964), so
+GPTQ is what makes this package usable. Rounding noise of 4-bit weights accumulates over 64 layers, so this 27B model
+sits at the level of d3:nano (95.7%) and below d3:mini (97.0%) on this measure. The image rows are lower than the text
+rows mainly because of the vision tower: on FastFlowLM's current vision kernels its features differ from the BF16
+tower's by a relative L2 error of 0.31 (the same kernels give 0.58 on the d3:mini tower, which ships).
+
+| Decision Index public-suite subset | this package on the NPU | upstream BF16 (same requests) |
+|---|---|---|
+| mean benchmark score (782 requests, 42 benchmarks) | 77.18 | 76.12 |
+| top-1 agreement with BF16 on the same requests (7,026 choice answers) | 98.9% | -- |
+
+Mean benchmark score, this package minus BF16: +1.06 pt (standard error 0.48 pt; request-weighted +1.31 pt). The package
+is not worse than the BF16 model on this slice (d3:lite -0.59 pt, d3:nano -1.25 pt, d3:mini -0.99 pt); the mean absolute
+probability difference is 0.0086. The slice is the first 800 requests of the same 4,002-request sample as d3:nano and
+d3:mini (round-robin over 43 benchmarks).
+
+| Decision Index public vision suite subset (600 questions, 10 benchmarks) | this package on the NPU | upstream BF16 |
+|---|---|---|
+| accuracy | 79.0% | 81.0% |
+| top-1 agreement with BF16 on the same questions | 88.8% | -- |
+
+Paired accuracy, BF16 minus this package: +2.0 pt (95% CI -0.3 to +4.3; d3:mini: +2.5 pt, CI +0.5 to +4.5). The largest
+gap is Hateful Memes moderation (63.3% vs 76.7% on 60 questions). The image rows are limited by the vision tower: on
+FastFlowLM's current vision kernels its features differ from the BF16 tower's by a relative L2 error of 0.31.
+
+The subset is a seeded round-robin sample over the suite's benchmarks (the same rows as for the d3:lite, nano and mini
+cards), not the full suite, so its scores are not comparable with the upstream board numbers (d3-turbo: 70.2 text, 72.9
+vision, upstream's own estimates). The vision subset is 60 seeded questions from each of 10 benchmarks (the suite
+without the gated Winoground).
+
+## Speed (AMD Ryzen AI MAX+ PRO 395 (Strix Halo, XDNA 2 NPU), 128 GB, Ubuntu 24.04, XRT, FastFlowLM)
+
+**These were measured on a loaded machine** (load average 10 to 80 from other jobs on the same box during most runs, CPU
+and memory bandwidth shared), so treat them as upper bounds; an idle machine is faster. The runs of the per-length and
+per-question-count tables used the plain Q4_K package of identical shape (the GPTQ package differs only in the rounded
+weight values); the HTTP rows used this package.
+
+Time to answer one request of one question of n tokens (the state is about 57% of the prompt):
+
+| question + state | median latency |
+|---|---|
+| 64 tokens | 5.6 s |
+| 330 tokens (HTTP: 4.9 s) | 5.5 s |
+| 1,024 tokens | 11.9 s |
+| 2,048 tokens | 23.4 s |
+| 4,096 tokens | 42.4 s |
+| 8,192 tokens | 84.3 s |
+| 16,384 tokens | 186 s |
+| 32,768 tokens | 430 s (360 to 411 s in the correctness runs) |
+
+The floor is about 4 to 5 s per request (the 15.5 GB of weights are streamed from memory once per pass, so a short
+question is memory-bound; d3:mini needs 0.5 s for the same question), then roughly 7 to 12 ms per token. Over HTTP
+(`flm serve`), the 736 text questions of the accuracy set (212 requests) took 4.4 s per request at the median.
+
+**Questions per request (state once).** One request about the same state, wall time of the engine (state 300 / 1,024 /
+4,096 tokens, each question about 110 tokens), against answering every question in its own pass:
+
+| questions | state 300 tokens | state 1,024 tokens | state 4,096 tokens |
+|---:|---|---|---|
+| 1 | 6.3 s | 12.4 s | 39.8 s |
+| 4 | 9.3 s (one pass each: 19.2 s, 2.1x) | 15.4 s (57.5 s, 3.7x) | 53.9 s (202 s, 3.7x) |
+| 16 | 21 s (53 s, 2.5x) | 25.9 s (243 s, 9.4x) | 72.7 s (635 s, 8.7x) |
+| 64 | 74 s (305 s, 4.1x) | 88.2 s (917 s, 10.4x) | 110 s (3,505 s, 32x) |
+| 255 | 318 s (1,220 s, 3.8x) | -- | -- |
+
+State once gives bit-identical answers to the one-pass-per-question path. Peak resident memory with 255 questions about a
+300-token state: 18 GB.
+
+| request (one box or track request, GPTQ package, loaded Strix Halo) | median latency |
+|---|---|
+| `box` questions about one image (3 to 8 boxes) | 11 s (3-19 s) |
+| a plain question about a video in the state | 18 s (4-26 s); 28 s for a 60 s 720p clip |
+| `assets` (images in options or instructions) | 28 s (11-114 s) |
+| `box` at one moment of a 60 s 720p video | 29 s |
+| `track` over a 60 s 720p video, 1 update per second (60 moments, 4 windows) | 145 s |
+| `track` over a 60 s 720p video, 2 updates per second (120 moments, 8 windows) | 278 s |
+
+
+From 1,536 tokens attention can run on the NPU's attention kernel; end to end it made no clear difference on this model
+(within the +-30% noise of the loaded machine), so the threshold was left at the default. The 32,768-token prompt is
+split into two GEMM parts internally (a single 2.3 GB buffer cannot be allocated on this driver).
+
+## Comparison
+
+- **Against upstream d3-turbo on one AMD Instinct MI325X** (AutoModel, 255 questions about one photo in 2.12 s, one
+  question in 302 ms): the NPU is memory-bandwidth bound and about two orders of magnitude slower in wall time (state
+  300 tokens + 255 questions: 318 s). Its use is local, private, low-power operation next to the CPU and GPU, not
+  throughput.
+- **Against the smaller NPU siblings:** d3:mini answers a 330-token question in 0.5 s and d3:nano in 0.25 s; d3:turbo
+  takes about 5 s, but reads a state once for any number of questions (the NPU siblings in FastFlowLM read the prompt again
+  for every question). On accuracy, upstream reports (its own estimates) 70.2 text / 72.9 vision on the Jev Decision
+  Index for d3-turbo against 66.3 / 71.3 for the d3 board model.
+- **Against the BF16 model on the same requests:** see Accuracy. The quantization costs a few points of top-1
+  agreement, more than for d3:mini, and the image path costs somewhat more than text.
+
+## License
+
+Apache-2.0, as the upstream model; see `LICENSE` and `NOTICE`. Built on Qwen/Qwen3.5-27B (Apache-2.0). Quantized and
+repackaged for FastFlowLM by the FastFlowLM team; the readout, decision config, tokenizer and chat template are unmodified.
+
+## Citation
+
+Please cite the upstream model ([vllm-sr/d3-turbo](https://huggingface.co/vllm-sr/d3-turbo)):
+
+```bibtex
+@misc{d3turbo_2026,
+  title        = {{d3-turbo}: A Multimodal Decision Model that Reads Once},
+  author       = {{vLLM Semantic Router Team}},
+  year         = {2026},
+  howpublished = {\url{https://huggingface.co/vllm-sr/d3-turbo}}
+}
+```

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 +1,147 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "model_type": "qwen3_5_text",
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "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,
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "mtp_num_hidden_layers": 1,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 24,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "use_cache": true,
+  "vocab_size": 248320,
+  "mamba_ssm_dtype": "float32",
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      11,
+      11,
+      10
+    ],
+    "rope_type": "default",
+    "rope_theta": 10000000,
+    "partial_rotary_factor": 0.25
+  },
+  "flm_version": "1.0.10",
+  "vision_model_weight": "vision_weight.q4nx",
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "vision_config": {
+    "vision_mm_engine_xclbin_name": "vision_mm.xclbin",
+    "vision_mha_engine_xclbin_name": "vision_attn.xclbin",
+    "QWEN3_5_PATCH_SIZE": 16,
+    "QWEN3_5_IMAGE_MERGE_SIZE": 2,
+    "QWEN3_5_SPATIAL_MERGE_SIZE": 2,
+    "QWEN3_5_SHORTEST_EDGE": 65536,
+    "QWEN3_5_LONGEST_EDGE": 1638400,
+    "QWEN3_5_VISION_RESCALE_FACTOR": 0.00392156862745098,
+    "QWEN3_5_VISION_RESCALE_IMAGE_MEAN": 0.5,
+    "QWEN3_5_VISION_RESCALE_IMAGE_STD": 0.5,
+    "QWEN3_5_TEMPORAL_PATCH_SIZE": 2,
+    "QWEN3_5_VISION_EMBED_DIM": 1152,
+    "QWEN3_5_VISION_NUM_HEADS": 16,
+    "QWEN3_5_VISION_HEAD_DIM": 72,
+    "QWEN3_5_VISION_MLP_INTERMEDIATE_SIZE": 4304,
+    "QWEN3_5_VISION_NUM_POSITION_EMBEDDINGS": 2304,
+    "QWEN3_5_VISION_NUM_LAYERS": 27,
+    "QWEN3_5_VISION_LAYER_NORM_EPSILON": 1e-06,
+    "QWEN3_5_VISION_OUT_HIDDEN_SIZE": 5120,
+    "VISION_MM_TILE_M": 128,
+    "VISION_MM_TILE_K": 256,
+    "VISION_MM_TILE_N": 64
+  },
+  "tie_word_embeddings": true,
+  "decision": {
+    "config": "decision_config.json",
+    "readout": "readout.safetensors",
+    "base_model": "vllm-sr/d3-turbo",
+    "revision": "v1.1",
+    "model_name": "d3-turbo"
+  }
+}

decision_config.json

@@ -0,0 +1,695 @@
+{
+  "format_version": 1,
+  "format_id": "d3-code-readout-v1",
+  "prompt": "d3",
+  "codes": [
+    "A",
+    "B",
+    "C",
+    "D",
+    "E",
+    "F",
+    "G",
+    "H",
+    "I",
+    "J",
+    "K",
+    "L",
+    "M",
+    "N",
+    "O",
+    "P",
+    "Q",
+    "R",
+    "S",
+    "T",
+    "U",
+    "V",
+    "W",
+    "X",
+    "Y",
+    "Z",
+    "AA",
+    "AB",
+    "AC",
+    "AD",
+    "AE",
+    "AF",
+    "AG",
+    "AH",
+    "AI",
+    "AJ",
+    "AK",
+    "AL",
+    "AM",
+    "AN",
+    "AO",
+    "AP",
+    "AQ",
+    "AR",
+    "AS",
+    "AT",
+    "AU",
+    "AV",
+    "AW",
+    "AX",
+    "AY",
+    "AZ",
+    "BA",
+    "BB",
+    "BC",
+    "BD",
+    "BE",
+    "BF",
+    "BG",
+    "BH",
+    "BI",
+    "BJ",
+    "BK",
+    "BL",
+    "BM",
+    "BN",
+    "BO",
+    "BP",
+    "BR",
+    "BS",
+    "BT",
+    "BU",
+    "BV",
+    "BW",
+    "BX",
+    "BY",
+    "CA",
+    "CB",
+    "CC",
+    "CD",
+    "CE",
+    "CF",
+    "CG",
+    "CH",
+    "CI",
+    "CK",
+    "CL",
+    "CM",
+    "CN",
+    "CO",
+    "CP",
+    "CR",
+    "CS",
+    "CT",
+    "CU",
+    "CV",
+    "CW",
+    "CX",
+    "CY",
+    "DA",
+    "DB",
+    "DC",
+    "DD",
+    "DE",
+    "DF",
+    "DG",
+    "DH",
+    "DI",
+    "DJ",
+    "DK",
+    "DL",
+    "DM",
+    "DN",
+    "DO",
+    "DP",
+    "DR",
+    "DS",
+    "DT",
+    "DU",
+    "DV",
+    "DW",
+    "DX",
+    "DY",
+    "EA",
+    "EB",
+    "EC",
+    "ED",
+    "EE",
+    "EF",
+    "EG",
+    "EH",
+    "EI",
+    "EK",
+    "EL",
+    "EM",
+    "EN",
+    "EO",
+    "EP",
+    "EQ",
+    "ER",
+    "ES",
+    "ET",
+    "EU",
+    "EV",
+    "EW",
+    "EX",
+    "EZ",
+    "FA",
+    "FB",
+    "FC",
+    "FD",
+    "FE",
+    "FF",
+    "FG",
+    "FH",
+    "FI",
+    "FK",
+    "FL",
+    "FM",
+    "FN",
+    "FO",
+    "FP",
+    "FR",
+    "FS",
+    "FT",
+    "FU",
+    "FW",
+    "FX",
+    "FY",
+    "GA",
+    "GB",
+    "GC",
+    "GD",
+    "GE",
+    "GF",
+    "GG",
+    "GH",
+    "GI",
+    "GL",
+    "GM",
+    "GN",
+    "GO",
+    "GP",
+    "GR",
+    "GS",
+    "GT",
+    "GU",
+    "GV",
+    "GW",
+    "GX",
+    "GY",
+    "HA",
+    "HB",
+    "HC",
+    "HD",
+    "HE",
+    "HF",
+    "HG",
+    "HH",
+    "HI",
+    "HK",
+    "HL",
+    "HM",
+    "HN",
+    "HO",
+    "HP",
+    "HQ",
+    "HR",
+    "HS",
+    "HT",
+    "HU",
+    "HV",
+    "HW",
+    "HX",
+    "HY",
+    "HZ",
+    "IA",
+    "IB",
+    "IC",
+    "ID",
+    "IE",
+    "IF",
+    "IG",
+    "IH",
+    "II",
+    "IJ",
+    "IK",
+    "IL",
+    "IM",
+    "IN",
+    "IO",
+    "IP",
+    "IQ",
+    "IR",
+    "IS",
+    "IT",
+    "IU",
+    "IV",
+    "IW",
+    "IX",
+    "IZ",
+    "JA",
+    "JB",
+    "JC",
+    "JD",
+    "JE",
+    "JI",
+    "JJ",
+    "JK",
+    "JM",
+    "JO",
+    "JP",
+    "JR",
+    "JS",
+    "JT"
+  ],
+  "token_ids": [
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39,
+    40,
+    41,
+    42,
+    43,
+    44,
+    45,
+    46,
+    47,
+    48,
+    49,
+    50,
+    51,
+    52,
+    53,
+    54,
+    55,
+    56,
+    57,
+    5840,
+    1803,
+    1646,
+    1745,
+    13276,
+    8018,
+    1825,
+    28946,
+    15015,
+    29595,
+    11568,
+    939,
+    1354,
+    1058,
+    18183,
+    2456,
+    88898,
+    905,
+    1846,
+    802,
+    33869,
+    7839,
+    14006,
+    2860,
+    2926,
+    22828,
+    6844,
+    9798,
+    4738,
+    9265,
+    11261,
+    19278,
+    36513,
+    93801,
+    8335,
+    14544,
+    85266,
+    9110,
+    28000,
+    15137,
+    4525,
+    25261,
+    12717,
+    7116,
+    17078,
+    14497,
+    57339,
+    74909,
+    52072,
+    19305,
+    4887,
+    12607,
+    3580,
+    6281,
+    2036,
+    9362,
+    8533,
+    2080,
+    10911,
+    2925,
+    3040,
+    9690,
+    27731,
+    8023,
+    6901,
+    8702,
+    6211,
+    1123,
+    16307,
+    18990,
+    64045,
+    63037,
+    33380,
+    6151,
+    3392,
+    5449,
+    3967,
+    1113,
+    5095,
+    51923,
+    49600,
+    17099,
+    51483,
+    17756,
+    16037,
+    8135,
+    30237,
+    5683,
+    9992,
+    7444,
+    5751,
+    10284,
+    20887,
+    59884,
+    52396,
+    16103,
+    67547,
+    18535,
+    8006,
+    7263,
+    1425,
+    6878,
+    14453,
+    9097,
+    44072,
+    76089,
+    68720,
+    2662,
+    2629,
+    923,
+    6548,
+    8924,
+    52194,
+    622,
+    1515,
+    1300,
+    37523,
+    44473,
+    36530,
+    3152,
+    93924,
+    3505,
+    15731,
+    6542,
+    14176,
+    11091,
+    1686,
+    11660,
+    80440,
+    18836,
+    26132,
+    5934,
+    24794,
+    40229,
+    3660,
+    11361,
+    10191,
+    8225,
+    3860,
+    78413,
+    17680,
+    15900,
+    78138,
+    15653,
+    5213,
+    22150,
+    39500,
+    10460,
+    35131,
+    21563,
+    43194,
+    27127,
+    3697,
+    20011,
+    24368,
+    15058,
+    23658,
+    8362,
+    16035,
+    24583,
+    52857,
+    38403,
+    60456,
+    81519,
+    40097,
+    16522,
+    29722,
+    21756,
+    18567,
+    1736,
+    48043,
+    87013,
+    22456,
+    23165,
+    55523,
+    13097,
+    50397,
+    41741,
+    23073,
+    6401,
+    86538,
+    16585,
+    11622,
+    2464,
+    84982,
+    75516,
+    36984,
+    58795,
+    47217,
+    59675,
+    5681,
+    3151,
+    1271,
+    887,
+    5203,
+    2685,
+    1849,
+    72470,
+    5370,
+    74063,
+    27629,
+    1655,
+    1728,
+    669,
+    3682,
+    3191,
+    59865,
+    2712,
+    1580,
+    922,
+    77243,
+    2990,
+    78493,
+    5228,
+    2750,
+    42711,
+    44568,
+    56402,
+    48236,
+    38993,
+    43559,
+    61250,
+    32942,
+    86302,
+    25310,
+    26313,
+    81770,
+    12185,
+    78382
+  ],
+  "temperature": 1.0,
+  "attention_mode": "prefix_bidir",
+  "pooling": "last",
+  "max_length": null,
+  "readout_dtype": "float32",
+  "validated_length": 32768,
+  "systemone": {
+    "question_types": [
+      "box",
+      "track"
+    ],
+    "image_placements": [
+      "state",
+      "instructions",
+      "criteria"
+    ],
+    "track_rates": [
+      1,
+      2
+    ],
+    "box_calibration": [
+      [
+        0.0,
+        0.0
+      ],
+      [
+        0.001953,
+        0.0
+      ],
+      [
+        0.003906,
+        0.0
+      ],
+      [
+        0.005859,
+        0.0
+      ],
+      [
+        0.007812,
+        0.030303
+      ],
+      [
+        0.017578,
+        0.045455
+      ],
+      [
+        0.052734,
+        0.144928
+      ],
+      [
+        0.119141,
+        0.173913
+      ],
+      [
+        0.181641,
+        0.375
+      ],
+      [
+        0.279297,
+        0.387755
+      ],
+      [
+        0.345703,
+        0.5
+      ],
+      [
+        0.361328,
+        0.571429
+      ],
+      [
+        0.376953,
+        0.571429
+      ],
+      [
+        0.449219,
+        0.637681
+      ],
+      [
+        0.53125,
+        0.666667
+      ],
+      [
+        0.587891,
+        0.666667
+      ],
+      [
+        0.591797,
+        0.769231
+      ],
+      [
+        0.615234,
+        0.783784
+      ],
+      [
+        0.65625,
+        0.8
+      ],
+      [
+        0.658203,
+        0.8
+      ],
+      [
+        0.701172,
+        0.889831
+      ],
+      [
+        0.753906,
+        0.905797
+      ],
+      [
+        0.802734,
+        0.93736
+      ],
+      [
+        0.884766,
+        0.956522
+      ],
+      [
+        0.890625,
+        0.971429
+      ],
+      [
+        0.898438,
+        0.972274
+      ],
+      [
+        0.951172,
+        0.986711
+      ],
+      [
+        0.964844,
+        0.997406
+      ],
+      [
+        0.982422,
+        1.0
+      ],
+      [
+        0.984375,
+        1.0
+      ],
+      [
+        0.986328,
+        1.0
+      ],
+      [
+        0.988281,
+        1.0
+      ],
+      [
+        0.990234,
+        1.0
+      ],
+      [
+        0.992188,
+        1.0
+      ],
+      [
+        0.994141,
+        1.0
+      ],
+      [
+        0.996094,
+        1.0
+      ],
+      [
+        0.998047,
+        1.0
+      ],
+      [
+        1.0,
+        1.0
+      ]
+    ],
+    "box_video_max_seconds": 60
+  }
+}

model.q4nx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb175d0ba981a2581242a8f279003306ec7decd9cc667178f755e2bab2558288
+size 15500905656

readout.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2579067a488138e2ef00bb3e98989cac7311afbf48700dfad02244e3671f241
+size 5222480

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|>"
+    }
+}

vision_weight.q4nx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b02b19596ebd66995bca905ecf481f994183e391505a89204caf965fe69425
+size 1037176592