Release

.gitattributes

@@ -0,0 +1,41 @@
+*.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
+figures/audio.png filter=lfs diff=lfs merge=lfs -text
+figures/hero.png filter=lfs diff=lfs merge=lfs -text
+figures/release.png filter=lfs diff=lfs merge=lfs -text
+figures/text.png filter=lfs diff=lfs merge=lfs -text
+figures/vision.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,331 @@
+---
+license: apache-2.0
+library_name: transformers
+base_model: google/gemma-4-E4B-it
+base_model_relation: finetune
+pipeline_tag: any-to-any
+language:
+- en
+tags:
+- decisions
+- typed-decisions
+- audio
+- vision
+- calibration
+- on-device
+- smaug
+- abacusai
+---
+<div align="center">
+  <picture>
+      <img src="https://cdn-avatars.huggingface.co/v1/production/uploads/63128dd099791aa61d180c72/dJ6uR23m09M-YEafBpmea.png" width="20%" alt="Smaug-Decisions">
+  </picture>
+</div>
+<hr>
+<div align="center" style="line-height:1">
+  <a href="https://abacus.ai" target="_blank"><img alt="Homepage" src="https://img.shields.io/badge/Homepage-Abacus.AI-white?color=1783ff&logoColor=white"/></a>
+  <a href="https://huggingface.co/abacusai" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Abacus.AI-ffc107?color=ffc107&logoColor=white"/></a>
+</div>
+<div align="center" style="line-height: 1;">
+  <a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/License-Apache_2.0-f5de53?&color=f5de53"/></a>
+  <a href="https://huggingface.co/abacusai/Smaug-Audio-Decisions-0.7B" target="_blank"><img alt="Fast tier" src="https://img.shields.io/badge/Fast_tier-Smaug--Audio--Decisions--0.7B-1783ff?&color=1783ff"/></a>
+  <a href="https://huggingface.co/abacusai/Smaug-Decisions-LiteRT" target="_blank"><img alt="On phones" src="https://img.shields.io/badge/On_phones-Smaug--Decisions--LiteRT-1783ff?&color=1783ff"/></a>
+</div>
+
+<p align="center"><b>State-of-the-art audio decisions in 4B parameters, and it sees and reads too.</b><br>
+60.1 Earshot audio skill, ahead of Gemini 4 Argon (59.4) and Gemini 3.8 Flash (50.5), and better calibrated than both.</p>
+
+## 1. Model Introduction
+
+Smaug-Decisions is a 4B decision model that hears, sees and reads. A fine-tune of Google's
+[Gemma 4 E4B-it](https://huggingface.co/google/gemma-4-E4B-it) by Abacus.AI, it answers a typed question about **audio, an image or
+text** with a calibrated probability per option, in one forward pass and with no generated text.
+
+<p align="center"><img src="figures/demo.svg" width="100%" alt="Four example decisions over audio, an image and text, each answered with a probability per option in one forward pass"></p>
+
+<p align="center"><img src="figures/stats.svg" width="100%" alt="60.1 Earshot audio skill, three input types, one forward pass per decision, 0.069 calibration error"></p>
+
+It is the only 4B decision model with results on all three input types. On audio it is ahead of the frontier APIs: **60.1** skill on
+**Earshot**, our 6,671-item audio decision benchmark, against 59.4 for Gemini 4 Argon and 50.5 for Gemini 3.8 Flash, and better
+calibrated than both (ECE 0.069 vs 0.123 and 0.204). On the public Jev Decision Index it scores **57.9** on images and **56.6** on text,
+the best Gemma 4 E4B on both.
+
+```python
+import sys
+from huggingface_hub import snapshot_download
+sys.path.insert(0, snapshot_download("abacusai/Smaug-Decisions", allow_patterns=["smaug_decide.py"]))
+from smaug_decide import SmaugDecide                                   # ships with this repo
+
+model = SmaugDecide.from_pretrained("abacusai/Smaug-Decisions")
+model("call.wav", "Has the speaker finished their turn?")               # -> {'Yes': 0.93, 'No': 0.07}
+```
+
+<p align="center"><img src="figures/matrix.svg" width="100%" alt="Every 4B decision model by input type: Smaug-Decisions is the only one with audio, image and text results"></p>
+
+## 2. Highlights
+
+- **Ahead of the frontier APIs on audio,** and better calibrated, so the probabilities work as thresholds.
+- **Hears, sees and reads:** audio up to 30 s, images and text through one prompt and one readout.
+- **One pass, no decoding:** about 200 ms per audio decision on an H100.
+- **Runs on phones:** [Smaug-Decisions-LiteRT](https://huggingface.co/abacusai/Smaug-Decisions-LiteRT) is 3.45 GB, keeps 59.4 audio skill and answers
+  a text question in about 0.6 s on an iPhone 14 Pro Max, fully offline.
+
+## 3. Model Summary
+
+<div align="center">
+<table>
+<tbody>
+<tr><td align="center"><strong>Architecture</strong></td><td align="center">Gemma 4 E4B-it (language model + audio and vision encoders); letter-logit readout</td></tr>
+<tr><td align="center"><strong>Parameters</strong></td><td align="center">4B effective, 8.6B stored (3.5B of the stored weights are embedding tables that are looked up, not computed; the Hugging Face counter shows the stored total)</td></tr>
+<tr><td align="center"><strong>Input</strong></td><td align="center">Audio up to 30 s (16 kHz mono), an image (560 image tokens), or text, plus a question with 2 to 20 options</td></tr>
+<tr><td align="center"><strong>Output</strong></td><td align="center">A calibrated probability per option (softmax for one answer, sigmoid for select-all)</td></tr>
+<tr><td align="center"><strong>Hardware</strong></td><td align="center">NVIDIA GPU (bfloat16), Apple Silicon (MPS) and CPU through Transformers; phones through <a href="https://huggingface.co/abacusai/Smaug-Decisions-LiteRT">Smaug-Decisions-LiteRT</a></td></tr>
+<tr><td align="center"><strong>Precision</strong></td><td align="center">bfloat16</td></tr>
+<tr><td align="center"><strong>Formats</strong></td><td align="center">Transformers (repo root); LiteRT-LM for phones (<a href="https://huggingface.co/abacusai/Smaug-Decisions-LiteRT">Smaug-Decisions-LiteRT</a>)</td></tr>
+<tr><td align="center"><strong>Base Model</strong></td><td align="center"><code>google/gemma-4-E4B-it</code></td></tr>
+<tr><td align="center"><strong>Adaptation</strong></td><td align="center">Full fine-tune</td></tr>
+</tbody>
+</table>
+</div>
+
+## 4. Evaluation
+
+### Audio: Earshot
+
+**Earshot** is our audio decision benchmark: 6,671 items and 17.2 hours of audio in four tracks: **conversation dynamics** (turn
+completion, next speaker, speaker count, speech activity; from VoxConverse, AMI and Smart Turn), **external turn completion** (Smart
+Turn v3.2 test), **sound and music** (genre, instrument, tempo, scene, sound events) and a small **pilot** track. **Audio skill** is
+the mean task skill per track, averaged over the tracks: 0 is guessing, 100 is perfect. No benchmark recording or item is in the
+training data.
+
+<p align="center"><img src="figures/earshot.svg" width="100%" alt="Earshot audio skill per track, and calibration error"></p>
+
+<details>
+<summary><b>Earshot table</b></summary>
+
+<div style="max-width:1100px;margin:0 auto">
+<table style="width:100%;table-layout:fixed;border-collapse:collapse;font-size:13px">
+<thead><tr><th style="padding:10px 6px;text-align:left;border-bottom:2px solid #2a78d6;width:26%"></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;font-weight:600;background:rgba(42,120,214,0.10);">Smaug-Decisions</th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;">Gemini 4 Argon<div style="font-size:10px;font-weight:400;color:#6B6B6B">(API)</div></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;">Gemini 3.8 Flash<div style="font-size:10px;font-weight:400;color:#6B6B6B">(API)</div></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;">AudioJev<div style="font-size:10px;font-weight:400;color:#6B6B6B">(Qwen2.5-Omni-3B)</div></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;">Gemma 4 E4B-it<div style="font-size:10px;font-weight:400;color:#6B6B6B">(zero-shot)</div></th>
+</tr></thead>
+<tbody>
+<tr><td colspan="6" style="padding:7px 10px;font-weight:600;color:#1a5fb4;background:#e8f0fc;border-bottom:1px solid rgba(42,120,214,0.2)">Earshot (audio decisions)</td></tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Audio skill (headline) &uarr;</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.47)"><strong>60.1</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.46)">59.4</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.40)">50.5</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.34)">43.6</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">5.0</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">ECE &darr;</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.47)"><strong>0.069</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.41)">0.123</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.33)">0.204</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.34)">0.191</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">0.464</td>
+</tr>
+<tr><td colspan="6" style="padding:7px 10px;font-weight:600;color:#1a5fb4;background:#e8f0fc;border-bottom:1px solid rgba(42,120,214,0.2)">Per track (skill) &uarr;</td></tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Conversation dynamics (3,000)</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.46)">48.2</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>49.6</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.46)">48.5</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.26)">26.7</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">3.6</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">External turn completion (1,000)</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.46)">80.8</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.44)">76.5</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>81.8</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.35)">62.0</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">11.2</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Sound &amp; music (1,115)</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.47)"><strong>66.1</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.46)">64.7</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.31)">42.4</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.41)">57.6</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">5.2</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Pilot (80)</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.45)">45.2</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>47.0</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.31)">29.1</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.30)">28.2</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">0.1</td>
+</tr>
+</tbody></table>
+<div style="font-size:11.5px;color:#6B6B6B;margin-top:6px">Bold = best in the row. Shading is relative within each row (darker = better). Every model scored on the same 6,671 items with the same harness; the APIs received the audio and returned JSON probabilities. Skill = (accuracy &minus; chance) / (1 &minus; chance), times 100.</div>
+</div>
+
+</details>
+
+Need it faster? [Smaug-Audio-Decisions-0.7B](https://huggingface.co/abacusai/Smaug-Audio-Decisions-0.7B) scores 53.0 on Earshot at 9.7 ms; in front of this
+model as a [cascade](https://huggingface.co/abacusai/Smaug-Audio-Decisions-0.7B#the-cascade) it matches this model's accuracy (60.1) at 130 ms
+instead of 210 ms.
+
+### Images and text: the public Jev Decision Index
+
+The matrix at the top has the headline numbers: 57.9 on images and 56.6 on text, the best Gemma 4 E4B on both (Winnow-E4B, the
+other Gemma 4 E4B fine-tune on the boards: 48.1 and 41.7). Images: our run of the official vision kit (0.4, public sets) at 560 image
+tokens.
+
+<details>
+<summary><b>Full Decision Index breakdown</b></summary>
+
+<p align="center"><img src="figures/text.svg" width="100%" alt="Text decision skill per area"></p>
+
+<div style="max-width:1100px;margin:0 auto">
+<table style="width:100%;table-layout:fixed;border-collapse:collapse;font-size:13px">
+<thead><tr><th style="padding:10px 6px;text-align:left;border-bottom:2px solid #2a78d6;width:26%"></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;font-weight:600;background:rgba(42,120,214,0.10);">Smaug-Decisions<div style="font-size:10px;font-weight:400;color:#6B6B6B">(audio + image + text)</div></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;">Perplexity Decider Flash<div style="font-size:10px;font-weight:400;color:#6B6B6B">(4B)</div></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;">vLLM-SR d3-mini<div style="font-size:10px;font-weight:400;color:#6B6B6B">(4B)</div></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;">RSI-Jev v6.1 VL<div style="font-size:10px;font-weight:400;color:#6B6B6B">(4B)</div></th>
+<th style="padding:10px 4px;text-align:center;font-weight:500;border-bottom:2px solid #2a78d6;color:#2a78d6;font-size:13px;">Winnow<div style="font-size:10px;font-weight:400;color:#6B6B6B">(Gemma 4 E4B)</div></th>
+</tr></thead>
+<tbody>
+<tr><td colspan="6" style="padding:7px 10px;font-weight:600;color:#1a5fb4;background:#e8f0fc;border-bottom:1px solid rgba(42,120,214,0.2)">Jev Decision Index 0.4.1, text (same 35 public benchmarks)</td></tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Public skill &uarr;</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.36)">56.6</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>61.8</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.36)">56.7</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.28)">52.9</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">41.7</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Knowledge &amp; reasoning</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.25)">35.1</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>46.0</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.44)">44.3</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.25)">35.2</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">25.3</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Language</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.45)">66.4</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>67.2</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.33)">60.4</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.30)">59.2</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">47.5</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Retrieval</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.46)">64.7</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>65.2</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.44)">63.6</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.31)">57.1</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">43.8</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Tools</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.29)">72.9</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>81.0</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.27)">72.0</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.18)">68.4</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">62.5</td>
+</tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Arts</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.36)">41.6</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.47)"><strong>46.6</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.28)">37.7</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.45)">45.7</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;background:rgba(42,120,214,0.05)">26.9</td>
+</tr>
+<tr><td colspan="6" style="padding:7px 10px;font-weight:600;color:#1a5fb4;background:#e8f0fc;border-bottom:1px solid rgba(42,120,214,0.2)">Earshot (audio decisions)</td></tr>
+<tr><td style="padding:8px 6px;padding-left:16px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600">Audio skill &uarr;</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;font-weight:600;background:rgba(42,120,214,0.47)"><strong>60.1</strong></td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;color:#9aa0a6">&mdash;</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;color:#9aa0a6">&mdash;</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;color:#9aa0a6">&mdash;</td>
+<td style="padding:8px 6px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:14px;color:#9aa0a6">&mdash;</td>
+</tr>
+</tbody></table>
+<div style="font-size:11.5px;color:#6B6B6B;margin-top:6px">Bold = best in the row. Other models: the public Decision Index board as of 2026-10-28 (text 0.4.1). Smaug-Decisions: our runs of the official Decision Index kit (text on a 3,000-row sample of the public suite, compared on the same 35 benchmarks); self-reported, not board submissions. &mdash; = no published result.</div>
+</div>
+
+</details>
+
+## 5. Training Approach
+
+- **Readout, not generation.** The answer is read from the LM-head logits of the option letters at the answer position (tanh
+  softcap 30, then softmax; select-all uses a sigmoid with one learned threshold). A decision costs one prefill.
+- **Decision-tuned and calibrated.** Full fine-tune of Gemma 4 E4B-it on a broad mix of typed decision tasks over audio, images and
+  text, with calibration as an explicit objective and options shuffled so the model learns the options, not their positions.
+
+## 6. Limitations
+
+- **Decisions, not text:** each call answers one typed question with a probability per option; the model does not write text.
+- **Per request:** one audio clip of up to 30 s (longer audio keeps its last 30 s), one image at 560 image tokens, up to 20 options.
+- **Thresholds:** set decision thresholds on your own data for high-stakes uses.
+
+## 7. Usage
+
+```bash
+pip install "transformers>=5.20" torch soundfile pillow huggingface_hub
+```
+
+```python
+import sys
+from huggingface_hub import snapshot_download
+sys.path.insert(0, snapshot_download("abacusai/Smaug-Decisions", allow_patterns=["smaug_decide.py"]))
+from smaug_decide import SmaugDecide
+
+model = SmaugDecide.from_pretrained("abacusai/Smaug-Decisions")      # CUDA, Apple Silicon (MPS) or CPU, picked automatically
+model("call.wav", "Has the speaker finished their turn?")                                  # predicate -> {'Yes': p, 'No': 1-p}
+model("song.wav", "Which genre is playing?", ["rock", "jazz", "classical"])                 # choice -> probabilities sum to 1
+model("room.wav", "Which sounds are present?", ["speech", "music", "alarm"], multi=True)    # select-all -> one probability each
+model("receipt.jpg", "Does the total exceed $50?")                                          # images
+model("The order never arrived.", "How upset is the customer?", ["calm", "annoyed", "angry"],
+      descriptions=["neutral tone", "complains", "threatens to leave"], rules="Judge the tone, not the facts.")
+```
+
+`from_pretrained` downloads the checkpoint (about 16 GB). Any runtime can reproduce the readout: run the prompt in
+`smaug_decide.render`, take the LM-head logits of the tokens `A`..`T` at the last position, apply the softcap from `readout.json`,
+then softmax (one answer) or `sigmoid(z - b)` with `b` from `readout.json` (select-all). With plain Transformers,
+`AutoModelForMultimodalLM.from_pretrained("abacusai/Smaug-Decisions", dtype="bfloat16")` loads the weights.
+
+### On phones
+
+[Smaug-Decisions-LiteRT](https://huggingface.co/abacusai/Smaug-Decisions-LiteRT) is this model in one **3.45 GB** file for Google's on-device
+runtime LiteRT-LM, running on the phone GPU. At about a fifth of the size it keeps almost all of this model's quality. It runs in
+the Cascade app on iPhone and Android next to [Smaug-Audio-Decisions-0.7B](https://huggingface.co/abacusai/Smaug-Audio-Decisions-0.7B), which answers the easy
+audio questions first. App source: [github.com/abacusai/Smaug-Decisions-Mobile](https://github.com/abacusai/Smaug-Decisions-Mobile).
+
+| | Smaug-Decisions (16 GB) | Smaug-Decisions-LiteRT (3.45 GB) | change |
+|---|---|---|---|
+| Earshot audio skill | 60.1 | **59.4** | &minus;0.7 |
+| Earshot calibration error (ECE, lower is better) | 0.069 | **0.074** | +0.005 |
+| Decision Index text | 56.6 | **53.9** | &minus;2.7 |
+| Decision Index images, 560 image tokens<sup>*</sup> | 57.2 | **55.1** | &minus;2.1 |
+| Decision Index images, 280 image tokens<sup>*</sup> | 54.8 | **51.8** | &minus;3.0 |
+
+Same items, same harness; the phone-build scores come from a PyTorch replica of the file's quantized weights. <sup>*</sup>10 of the 11 public
+vision sets (Winoground left out; this model's 11-set index is 57.9).
+
+| iPhone 14 Pro Max (6 GB RAM, phone GPU) | measured |
+|---|---|
+| first load (one time) / later loads | 13-21 s / 0.48 s |
+| text decision | ~0.6 s |
+| audio decision | ~1.6 s |
+| image decision (280 image tokens) | ~7.4 s |
+| peak app memory, with Smaug-Audio-Decisions-0.7B loaded | 1.35 GB |
+| storage | the 3.45 GB file + a ~2.4 GB cache written on first load |
+
+## 8. License
+
+Apache 2.0, the same license as the base model, Gemma 4 E4B-it.
+
+## 9. Citation
+
+```bibtex
+@misc{abacusai2026smaugdecisions,
+  title  = {Smaug-Decisions: calibrated typed decisions over audio, images and text},
+  author = {Abacus.AI},
+  year   = {2026},
+  url    = {https://huggingface.co/abacusai/Smaug-Decisions}
+}
+```
+
+## 10. Contact Us
+
+If you have any questions, please reach out at [Abacus.AI](https://abacus.ai).

chat_template.jinja

@@ -0,0 +1,386 @@
+{#
+  Template: Google Gemma 4 Canonical Chat Template
+  Author: Google Gemma Engineering Team
+  Published: 2026-07-09
+  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
+#}
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if not filter_keys or key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'OBJECT' -%}
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                    }
+                {%- elif value is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is none -%}
+        {{- 'null' -}}
+    {%- elif argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+
+{#- ===== SETUP ===== -#}
+{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
+{%- set loop_messages = messages -%}
+{%- set enable_thinking = enable_thinking | default(false) -%}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
+    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+    {%- endif -%}
+
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
+    {%- if thinking_text and thinking_gate -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message.get('tool_calls') -%}
+                {%- for tool_call in message.get('tool_calls') -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is none -%}
+                    {%- else -%}
+                        {{- raise_exception(
+                            "chat_template: tool_calls[].function.arguments must be a "
+                            "JSON object (mapping), not a string. Deserialize arguments "
+                            "before passing to the template."
+                        ) -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message.get('tool_responses') -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
+                        {%- for tc in message.get('tool_calls') -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') in ['image', 'image_url'] -%}
+                                    {{- '<|image|>' -}}
+                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
+                                    {{- '<|audio|>' -}}
+                                {%- elif part.get('type') == 'video' -%}
+                                    {{- '<|video|>' -}}
+                                {%- endif -%}
+                            {%- endfor -%}
+                        {%- else -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- endif -%}
+                        {%- set ns_tr_out.flag = true -%}
+                        {%- set ns.prev_message_type = 'tool_response' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+            {%- set captured_content -%}
+            {%- if message.get('content') is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message.get('content') is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item.get('type') == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item.get('type') in ['image', 'image_url'] -%}
+                        {{- '<|image|>' -}}
+                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
+                        {{- '<|audio|>' -}}
+                    {%- elif item.get('type') == 'video' -%}
+                        {{- '<|video|>' -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {#- Forward-scan: find next non-tool message role for continuation detection -#}
+        {%- set next_nt = namespace(role=None, found=false) -%}
+        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
+            {%- if not next_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set next_nt.role = loop_messages[j]['role'] -%}
+                    {%- set next_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+
+        {%- set continues_into_next = (
+            role == 'model'
+            and next_nt.role == 'assistant'
+            and (not message.get('tool_calls') or ns_tr_out.flag)
+        ) -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif continues_into_next -%}
+        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+
+    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
+    {%- set ns.prev_non_tool_role = message['role'] -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,187 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_proj_dims": 1536,
+    "residual_weight": 0.5,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "float32",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 18,
+    "pad_token_id": 0,
+    "per_layer_config": {
+      "05": {
+        "head_dim": 512
+      },
+      "11": {
+        "head_dim": 512
+      },
+      "17": {
+        "head_dim": 512
+      },
+      "23": {
+        "head_dim": 512
+      },
+      "29": {
+        "head_dim": 512
+      },
+      "35": {
+        "head_dim": 512
+      },
+      "41": {
+        "head_dim": 512
+      }
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.20.2",
+  "video_token_id": 258884,
+  "vision_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "axial"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.20.2"
+}

head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f06a9992a8cf0a33726bcf23749ab52f7c832d05af2e1348eb53c45cb13ece
+size 1556

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7272eca31e37083c41362c5453dcb1cea6c29d4cb2af985283e3c5931c3b6e
+size 17224656900

processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

readout.json

@@ -0,0 +1,6 @@
+{
+ "final_logit_softcapping": 30.0,
+ "multi_bias_b": 8.010554313659668,
+ "letters": "ABCDEFGHIJKLMNOPQRST",
+ "image_soft_tokens": 560
+}

smaug_decide.py

@@ -0,0 +1,121 @@
+"""Calibrated typed decisions over audio, images or text by Abacus.AI: one forward pass, a probability per option, no generated text.
+
+    from smaug_decide import SmaugDecide
+    model = SmaugDecide.from_pretrained('abacusai/Smaug-Decisions')
+    model('clip.wav', 'Has the speaker finished their turn?')                      # -> {'Yes': 0.93, 'No': 0.07}
+    model('clip.wav', 'Which genre is playing?', ['rock', 'jazz', 'classical'])    # -> one-answer: probabilities sum to 1
+    model('clip.wav', 'Which sounds are present?', ['speech', 'music', 'alarm'], multi=True)   # -> select-all: one probability each
+    model('photo.jpg', 'Is there a person in the picture?')                        # images and plain text work the same way
+    model('The order never arrived.', 'How upset is the customer?', ['calm', 'annoyed', 'angry'])
+
+The readout is the model's own LM-head logits for the option letters A..T at the answer position (softcapped), softmax for one-answer
+questions and sigmoid(z - b) for select-all questions; `b` is the learned select-all threshold stored in readout.json / head.pt.
+Runs on NVIDIA GPUs (bfloat16), Apple Silicon (MPS) and CPU; the device is picked automatically.
+"""
+import json
+import os
+
+import numpy as np
+import soundfile as sf
+import torch
+from huggingface_hub import snapshot_download
+from PIL import Image
+from transformers import AutoModelForMultimodalLM, AutoProcessor
+
+
+LETTERS = 'ABCDEFGHIJKLMNOPQRST'
+SAMPLE_RATE, MAX_AUDIO_SECONDS = 16000, 30.0            # the model hears 16 kHz mono; longer clips keep their last 30 s
+MAX_TOKENS, AUDIO_TOKENS_PER_SECOND, IMAGE_TOKENS = 3072, 25, 560   # images at 560 soft tokens, as trained and evaluated
+PREAMBLE = ('You make decisions for apps. Read the rules, the context and the input, then answer the question by choosing '
+            'from the lettered options.')
+IMAGE_SUFFIXES = ('.jpg', '.jpeg', '.png', '.webp', '.gif', '.bmp')
+AUDIO_SUFFIXES = ('.wav', '.flac', '.ogg', '.mp3', '.m4a', '.aiff', '.aif')
+WEIGHT_FILES = ['*.json', '*.jinja', 'model*.safetensors', 'head.pt']   # the checkpoint at the repo root
+
+
+def trim(s, n):
+    if len(s) <= n:
+        return s
+    return s[:int(n * 0.7)] + ' ... ' + s[-int(n * 0.3):]
+
+
+def render(question, options, descriptions, multi, media_tag, rules, context, text_input, char_budget):
+    """The training prompt, verbatim: preamble, optional rules / context, the input, the lettered options, the answer instruction."""
+    parts = [PREAMBLE]
+    if rules:
+        parts.append(f'Rules: {trim(rules, char_budget // 2)}')
+    if context:
+        parts.append(f'Context: {trim(context, char_budget)}')
+    if media_tag:
+        parts.append(f'Input: {media_tag}')
+    elif text_input:
+        parts.append(f'Input: {trim(text_input, char_budget)}')
+    lines = [f'Question: {question}' + (' Select all that apply.' if multi else '')]
+    for k, (opt, desc) in enumerate(zip(options, descriptions)):
+        lines.append(f'{LETTERS[k]}) {opt}' + (f' — {desc}' if desc else ''))
+    parts.append('\n'.join(lines))
+    parts.append('Answer with the letters of all options that apply.' if multi else 'Answer with the letter of the best option.')
+    return '<bos><|turn>user\n' + '\n'.join(parts) + '<turn|>\n<|turn>model\n'
+
+
+def load_audio(x):
+    """A path, or a (samples, sample_rate) pair, or a 1-D float array at 16 kHz -> mono float32 at 16 kHz, last 30 s."""
+    if isinstance(x, str):
+        w, sr = sf.read(x, dtype='float32')
+    elif isinstance(x, tuple):
+        w, sr = x
+    else:
+        w, sr = x, SAMPLE_RATE
+    w = np.asarray(w, dtype=np.float32)
+    if w.ndim > 1:
+        w = w.mean(1)
+    if sr != SAMPLE_RATE:   # linear resampling is enough for a reference script; use a proper resampler for production audio
+        n = int(round(len(w) * SAMPLE_RATE / sr))
+        w = np.interp(np.linspace(0.0, len(w) - 1, n), np.arange(len(w)), w).astype(np.float32)
+    return w[-int(MAX_AUDIO_SECONDS * SAMPLE_RATE):]
+
+
+class SmaugDecide:
+    def __init__(self, model, processor, readout, device):
+        self.model, self.proc, self.device = model.eval(), processor, device
+        tok = processor.tokenizer
+        self.letter_ids = torch.tensor([tok(L, add_special_tokens=False)['input_ids'][0] for L in LETTERS], device=device)
+        self.cap, self.b = readout.get('final_logit_softcapping'), float(readout['multi_bias_b'])
+
+    @classmethod
+    def from_pretrained(cls, name_or_path, device=None):
+        path = name_or_path if os.path.isdir(name_or_path) else snapshot_download(name_or_path, allow_patterns=WEIGHT_FILES)
+        device = device or ('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
+        model = AutoModelForMultimodalLM.from_pretrained(path, dtype=torch.bfloat16).to(device)
+        readout = json.load(open(os.path.join(path, 'readout.json')))
+        return cls(model, AutoProcessor.from_pretrained(path), readout, device)
+
+    @torch.no_grad()
+    def __call__(self, inp, question, options=('Yes', 'No'), descriptions=None, multi=False, rules=None, context=None):
+        """inp: an audio path / (samples, sr) / 16 kHz array, an image path / PIL image, or a plain string. Returns {option: probability}."""
+        options = list(options)
+        assert 2 <= len(options) <= len(LETTERS), f'2 to {len(LETTERS)} options'
+        descriptions = list(descriptions) if descriptions else [None] * len(options)
+        audio = image = text_input = None
+        if isinstance(inp, Image.Image) or (isinstance(inp, str) and inp.lower().endswith(IMAGE_SUFFIXES)):
+            image = (inp if isinstance(inp, Image.Image) else Image.open(inp)).convert('RGB')
+        elif isinstance(inp, str) and not inp.lower().endswith(AUDIO_SUFFIXES) and not os.path.exists(inp):
+            text_input = inp
+        else:
+            audio = load_audio(inp)
+        media_tokens = len(audio) / SAMPLE_RATE * AUDIO_TOKENS_PER_SECOND + 2 if audio is not None else (IMAGE_TOKENS + 2 if image is not None else 0)
+        tag = '<|audio|>' if audio is not None else '<|image|>' if image is not None else None
+        budget = int(max(400, (MAX_TOKENS - media_tokens - 80 - 10 * len(options)) * 3.5))
+        text = render(question, options, descriptions, multi, tag, rules, context, text_input, budget)
+        kw = {}
+        if audio is not None:
+            kw['audio'] = [audio]
+        if image is not None:
+            kw['images'] = [image]; kw['images_kwargs'] = {'max_soft_tokens': IMAGE_TOKENS}
+        enc = self.proc(text=[text], return_tensors='pt', add_special_tokens=False, **kw).to(self.device)
+        h = self.model.model(**enc, use_cache=False).last_hidden_state[0, -1].float()          # hidden state at the answer position
+        z = h @ self.model.lm_head.weight[self.letter_ids[:len(options)]].float().T          # LM-head logits of the letters only
+        if self.cap:
+            z = torch.tanh(z / self.cap) * self.cap
+        p = torch.sigmoid(z - self.b) if multi else torch.softmax(z, -1)
+        return dict(zip(options, p.tolist()))

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,142 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "fields": {
+      "content": {
+        "close": [
+          "<turn|>",
+          "<|tool_response>",
+          "<eos>"
+        ],
+        "content": "text"
+      },
+      "thinking": {
+        "close": "<channel|>",
+        "content": "text",
+        "open": "<|channel>thought\n"
+      },
+      "tool_calls": {
+        "close": "<tool_call|>",
+        "content": "json",
+        "content_args": {
+          "string_delims": [
+            [
+              "<|\"|>",
+              "<|\"|>"
+            ]
+          ],
+          "unquoted_keys": true
+        },
+        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
+        "repeats": true,
+        "transform": {
+          "function": {
+            "arguments": "{content}",
+            "name": "{name}"
+          },
+          "type": "function"
+        }
+      }
+    },
+    "start_anchor": [
+      "<|turn>model\n",
+      "<tool_response|>"
+    ]
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}