Add files using upload-large-folder tool

.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
+docs/assets/three_tests.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gguf/CrossbowReviewer-9B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

LICENSE

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

NOTICE

@@ -0,0 +1,6 @@
+CrossbowReviewer-9B
+Copyright 2026 riposta
+
+This model is a fine-tuned derivative of Qwen3.5-9B-Base (https://huggingface.co/Qwen/Qwen3.5-9B-Base)
+by the Qwen Team, Alibaba Cloud, licensed under the Apache License, Version 2.0.
+The fine-tuned weights are distributed under the same license (see LICENSE).

README.md

@@ -0,0 +1,130 @@
+---
+base_model: Qwen/Qwen3.5-9B-Base
+base_model_relation: finetune
+license: apache-2.0
+library_name: transformers
+language:
+  - en
+tags:
+  - code-review
+  - static-analysis
+  - typed-decisions
+  - calibration
+  - systemone
+  - qwen3.5
+  - gguf
+  - local-inference
+---
+
+# CrossbowReviewer-9B
+
+**Calibrated code review decisions in one forward pass. It asks up to 107 rules per file, runs in ~0.2 s on an A100
+and in ~3 s on a Mac with the Q8_0 GGUF.**
+
+CrossbowReviewer-9B fine-tunes [Qwen3.5-9B-Base](https://huggingface.co/Qwen/Qwen3.5-9B-Base) for
+[Jev](https://docs.typesafe.ai/concepts/system-one)-style typed decisions about code. It writes no review text. For
+each question, such as "is this free of SQL injection?" or "does each class have one reason to change?", it returns
+a choice, a calibrated confidence and the full distribution. Its [inference server](https://github.com/riposta/CrossbowReviewer)
+provides a `/v1/systemone` endpoint that follows the Jev request schema.
+
+- **Typed decisions:** `noul` (yes/no), `choice` (up to 26 options) and `score` (2–10 levels), asked against the code
+  as `state`.
+- **One pass:** all questions share one prefill. Option-letter logits are read at each answer slot, so no answer text
+  is generated.
+- **120 built-in rules:** SOLID and design principles, patterns and anti-patterns, correctness, error handling,
+  security (OWASP / CWE), performance, readability, clean code, testability, testing, API design and language idioms.
+  Two aggregate questions are included (`primary_category`, `severity`).
+- **7 languages:** Java, Python, TypeScript, JavaScript, Go, C#, Rust.
+- **Full weights:** no adapter and no conversion step. Safetensors work with transformers; GGUF works with llama.cpp.
+
+[Inference server](https://github.com/riposta/CrossbowReviewer) · [Quickstart](docs/QUICKSTART.md) ·
+[Benchmarks](docs/BENCHMARKS.md) · [Artifact manifest](release-manifest.json)
+
+## Downloads
+
+| Files | Format and use | Size |
+|---|---|---:|
+| `model-0000{1..4}-of-00004.safetensors` + configs | **BF16 safetensors.** transformers backend (CUDA, Apple MPS, CPU) | 17.9 GB |
+| [`gguf/CrossbowReviewer-9B-Q8_0.gguf`](https://huggingface.co/riposta/CrossbowReviewer-9B/resolve/main/gguf/CrossbowReviewer-9B-Q8_0.gguf?download=true) | **Q8_0 GGUF.** llama.cpp backend; fits 12 GB GPUs and Apple Silicon | 9.5 GB |
+
+`decision_config.json` holds what turns logits into decisions: the fitted temperature (1.044), the option letters and
+the prompt format. Both backends read it.
+
+The Q8_0 GGUF gives the same answers as the BF16 safetensors. On a parity set of 79 decisions every choice matched,
+with a mean probability difference of 0.004.
+
+## Quick start
+
+```bash
+git clone https://github.com/riposta/CrossbowReviewer && cd CrossbowReviewer
+uv run uvicorn server:app --port 8000     # transformers backend; downloads this repo on first request
+curl -s localhost:8000/v1/systemone -H 'content-type: application/json' \
+  -d '{"state": {"language": "python", "code": "def add(items=[]):\n    items.append(1)\n    return items"}}'
+```
+
+Without `questions`, every rule for `state.language` is asked. `yes` means compliant:
+
+```json
+{"decisions": {"py_mutable_default": {"choice": "no", "confidence": 0.98, "distribution": {"yes": 0.02, "no": 0.98}}, "...": "..."}}
+```
+
+For llama.cpp, custom questions and all options, see [docs/QUICKSTART.md](docs/QUICKSTART.md).
+
+## Results
+
+| Balanced accuracy (0.5 = chance) | Synthetic | Synthetic, relabeled by independent judges | OWASP Benchmark (human labels) | Real open-source code |
+|---|---:|---:|---:|---:|
+| **CrossbowReviewer-9B** | 0.824 | **0.841** | 0.654 | **0.783** |
+| Jev (jev-1.13.0) | 0.809 | 0.813 | 0.653 | 0.717 |
+| Qwen3.5-9B-Base | 0.644 | 0.648 | 0.696 | 0.517 |
+| Claude Opus 5.5 (reasoning) | 0.925 | — | 0.979 | 0.831 |
+| GPT-6 Sol (reasoning) | 0.911 | — | 0.900 | 0.926 |
+
+![Three tests](docs/assets/three_tests.png)
+
+- **Calibration:** expected calibration error is **0.016** on the synthetic test and **0.006** on real code. When the
+  model says 0.9, it is right about 90% of the time.
+- **Latency:** the reasoning models are 3–7 points more accurate, but 25–55× slower (8–10 s per file versus ~0.2 s).
+
+![Quality vs latency](docs/assets/quality_vs_latency.png)
+
+Methodology, per-category results and all metrics are in [docs/BENCHMARKS.md](docs/BENCHMARKS.md) and
+[docs/benchmarks.json](docs/benchmarks.json).
+
+## Limitations — read before use
+
+**Security taint traps.** On OWASP Benchmark the model flags 94% of vulnerable cases. It recognizes only **26% of the
+safe cases built to look vulnerable**, for example when tainted input reaches only a dead branch or is overwritten by
+a constant. Jev (24%) and the base model (37%) share this weakness. One forward pass cannot trace data flow the way a
+reasoning model can (Opus 5.5: 94%). Extra training on 500 hard security cases raised this to 42%, which is not
+enough, so that version is not released.
+
+![OWASP traps](docs/assets/owasp_traps.png)
+
+**Recommended use.** Use the model directly for design, readability, correctness, testing and idiom rules. For
+data-flow security rules (`injection`, `path_traversal`, `xss`, `ssrf`, `open_redirect`), treat a `no` as "needs a
+closer look" and escalate it to a reasoning model.
+
+**Other limits:**
+- **Synthetic training data.** About 1 500 snippets (30–120 lines) were written and labeled by LLMs. They are not
+  human reviews of real pull requests. Scores on synthetic data overstate real-world accuracy.
+- **One file at a time.** The model judges snippets, not diffs, and does not see the rest of the codebase.
+- **Custom questions** outside the 120 trained rules use the same format, but their quality is not measured.
+- **Prompts are in English.** `choice` supports up to 26 options (Jev: 255).
+
+## Training
+
+- **Data:** 1 466 synthetic snippets. Each one is built as language × rule × (compliant / violating), and all ~107
+  questions are labeled by an LLM. The label agrees with the construction target in 93% of cases. A judge-in-the-loop
+  added 51 samples for the weakest rules.
+- **Method:** LoRA on all linear layers (rank 16, alpha 32; 0.48% of parameters), merged into these full weights.
+  Cross-entropy over option-letter logits at every answer slot. Each sample shows a random 8–all subset of questions,
+  always including its target rule. 30% of samples omit `language`.
+- **Optimization:** 3 rounds × 1 epoch, AdamW, lr 1e-4, effective batch 8, bf16, 1× A100 40 GB (~2 h).
+- **Calibration:** a single temperature fitted on a validation split.
+- **Not included:** the multi-token-prediction head of the base model is not shipped (`mtp_num_hidden_layers: 0`),
+  because decisions never generate text.
+
+## License
+
+Apache 2.0, the same as the base model. See [LICENSE](LICENSE) and [NOTICE](NOTICE).

SHA256SUMS

@@ -0,0 +1,21 @@
+cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30  LICENSE
+930472a7a4b21e39db2a68aafcb1cc09984a4c7f88e6072682eef75b2ec844b2  NOTICE
+3afbcc1e7114e388a43f93a780b3f09f622550bc721d0e633f91dafd736595be  README.md
+a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715  chat_template.jinja
+888a884d9ce35c4df383c9f7ed3d6466ee0a4d92cc9f44f12315ea850bb0b345  config.json
+86a9041d7151d9479733c0cd5ae40bd247ab4607d1b71e21b6c8c71b4eafb359  decision_config.json
+8288b734ae8bda221cfd355a6b99f7cdfa93290000bfce86e6eef2cbf53ccfde  docs/BENCHMARKS.md
+1f8496c6b8ce1e69660df2bcb09bc991150c42622551a2e2c09df974a1ac151c  docs/QUICKSTART.md
+1ab1f4cac1f59f0f42f9ca5f327fc73c6b3618fd76381951a5ea7e9d52de54c7  docs/assets/owasp_traps.png
+21bc5f2530bd4aa5f23b74734bc4d94ef327d7cc4cd6380b842569c609e03c04  docs/assets/quality_vs_latency.png
+0ec945c553c90b82cd211fcbc48fc508007c2b87c47e067bfb8d636ddfb06c86  docs/assets/three_tests.png
+031a3518ca6b51b9687bd28bbf00476ee08c6b05171ef8900070798dcbe73016  docs/benchmarks.json
+62153eb6c69f2e1f426beaa8002b7186437e949c7588167085df14e10e9c0a73  generation_config.json
+9dc38b76a9490008da3f73fa80acd4bc530a08cecd43b898be61e071e7bc6cf9  gguf/CrossbowReviewer-9B-Q8_0.gguf
+954b02ec2423fdd271f32a7ddc306f725f1167a769d69d39f7353e86cdb6eddb  model-00001-of-00004.safetensors
+d58e7dba95a4e9fe62e129c3fcce41ae0c28282be660fe8eadca4930b18e106d  model-00002-of-00004.safetensors
+5a735fdc0957f9132ccb8006e57bf3f392168b2e870747728b48484e8135c000  model-00003-of-00004.safetensors
+a26dda3f020b8b2f5ff3f636a9a528db34bccf176f3718c469f35e9ee776df0d  model-00004-of-00004.safetensors
+e8ef36c3e0c658f657e282fb6d68609770f039ef2886b89f8ca6a1a293422408  model.safetensors.index.json
+06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523  tokenizer.json
+8671bed7c852ce9e661be94f179a7b4ffd091c2a65aea0363e5501c20318ee45  tokenizer_config.json

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- 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 +1,83 @@
+{
+  "architectures": [
+    "Qwen3_5ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "mamba_ssm_dtype": "float32",
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_5_text",
+  "mtp_num_hidden_layers": 0,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      11,
+      11,
+      10
+    ],
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.17.0",
+  "use_cache": true,
+  "vocab_size": 248320
+}

decision_config.json

@@ -0,0 +1,20 @@
+{
+  "format": "crossbow-slots-v1",
+  "temperature": 1.043660283088684,
+  "option_letters": "ABCDEFGHIJKLMNOPQRSTUVWXYZ",
+  "letter_prefix": " ",
+  "prompt_header": "You are a code review decision engine. Each question is answered with a single option letter.\n\nState:\n",
+  "question_template": "\n\n### {name}\n{instructions}\n{options}\nAnswer:",
+  "option_template": "{letter}. {option}",
+  "option_with_criteria_template": "{letter}. {option}: {description}",
+  "noul_options": [
+    "yes",
+    "no"
+  ],
+  "max_choice_options": 26,
+  "score_levels": [
+    2,
+    10
+  ],
+  "base_model": "Qwen/Qwen3.5-9B-Base"
+}

docs/BENCHMARKS.md

@@ -0,0 +1,69 @@
+# Benchmarks
+
+We used four tests, from the most in-distribution to the most independent. Every system answers exactly the questions
+each sample is labeled for. All numbers are also in [benchmarks.json](benchmarks.json).
+
+| Test | Code | Labels | Samples |
+|---|---|---|---|
+| Synthetic | 360 LLM-written snippets, 12 categories × 30, half compliant | consensus of two LLM judges | 360 (3 271 labels) |
+| Synthetic, relabeled | the same snippets | consensus of Claude Opus 5.5 and GPT-6 Sol (not used in training) | 359 (2 815 labels) |
+| [OWASP Benchmark](https://github.com/OWASP-Benchmark/BenchmarkJava) v1.2 | 435 Java servlets, 9 categories → 5 rules | **humans, by construction** | 435 |
+| Real open-source code | 55 files (30–150 lines) from 9 popular repositories, 7 languages | consensus of two frontier LLM judges (92% agreement) | 55 (5 401 labels, 6.9% violations) |
+
+**OWASP preparation:** everything that reveals the label was stripped. That covers servlet paths holding the
+category name, `BenchmarkTest` names and comments.
+
+**Test data is not redistributed:** OWASP Benchmark is GPL-2.0, and the source files belong to their authors.
+
+## Headline
+
+| System | Synthetic index (95% CI) | Relabeled index | OWASP bal_acc | Real code bal_acc | ECE synthetic / real |
+|---|---|---|---|---|---|
+| **CrossbowReviewer-9B** | 85.7 (84.1–87.3) | **87.5** | 0.654 | **0.783** | **0.016 / 0.006** |
+| Jev (jev-1.13.0) | 82.3 (80.7–83.8) | 85.0 | 0.653 | 0.717 | 0.043 / 0.030 |
+| Qwen3.5-9B-Base | 70.3 (68.2–72.5) | 71.4 | 0.696 | 0.517 | 0.040 / 0.031 |
+| Claude Opus 5.5 | 92.9 (91.7–93.8) | — (judge) | 0.979 | 0.831 | 0.113 / 0.086 |
+| GPT-6 Sol | 89.1 (87.6–90.6) | — (judge) | 0.900 | 0.926* | 0.046 / 0.036 |
+
+**Metrics:**
+- **Index:** mean accuracy over rule categories × 100. Every category weighs the same.
+- **bal_acc:** mean recall over the gold options per question. It matters because most real-code labels are "yes".
+- **ECE:** expected calibration error.
+
+\* The real-code judges come from the same model families as the frontier systems compared here, so frontier scores
+on real code are likely inflated. The small models are not affected.
+
+## OWASP Benchmark: taint traps
+
+| System | Vulnerable flagged | Safe recognized |
+|---|---:|---:|
+| Claude Opus 5.5 | 1.00 | 0.94 |
+| GPT-6 Sol | 1.00 | 0.75 |
+| Qwen3.5-9B-Base | 0.93 | 0.37 |
+| **CrossbowReviewer-9B** | 0.94 | 0.26 |
+| Jev | 0.97 | 0.24 |
+
+![OWASP traps](assets/owasp_traps.png)
+
+The single-pass models and Jev flag almost every security-looking case, including traps where the tainted value never
+reaches the sink. Reasoning models trace the data flow. An unreleased follow-up trained on 500 extra hard security
+cases reached 0.42 safe recognized. That is not enough to change the conclusion: **escalate data-flow security "no"
+answers to a reasoning model.**
+
+## Latency
+
+| System | Seconds per file | Hardware |
+|---|---:|---|
+| CrossbowReviewer-9B (transformers, BF16) | 0.18 | 1× A100 40 GB |
+| CrossbowReviewer-9B (llama.cpp, Q8_0) | ~3 | Apple M5 Pro (Metal) |
+| Jev | 0.32 | API |
+| Claude Opus 5.5 | 8.2 | API |
+| GPT-6 Sol | 9.8 | API |
+
+![Quality vs latency](assets/quality_vs_latency.png)
+
+## Reproducibility
+
+- **Determinism:** a second benchmark run of the same weights gave identical results.
+- **Formats:** the merged safetensors match the original base + LoRA (79/79 identical choices, mean |Δp| 0.003). The
+  Q8_0 GGUF matches the safetensors (79/79, mean |Δp| 0.004).

docs/QUICKSTART.md

@@ -0,0 +1,74 @@
+# Quickstart
+
+The inference server lives at [github.com/riposta/CrossbowReviewer](https://github.com/riposta/CrossbowReviewer). It
+has two backends that return the same decisions.
+
+| Backend | Weights | Hardware | Speed (one file, ~16 questions) |
+|---|---|---|---|
+| `transformers` (default) | BF16 safetensors (17.9 GB) | CUDA GPU ≥ 24 GB, Apple Silicon ≥ 32 GB, or CPU | ~0.2 s on an A100 |
+| `llamacpp` | Q8_0 GGUF (9.5 GB) | GPU ≥ 12 GB, Apple Silicon ≥ 16 GB, or CPU | ~3 s on an M5 Pro (Metal) |
+
+## transformers backend
+
+```bash
+git clone https://github.com/riposta/CrossbowReviewer && cd CrossbowReviewer
+uv run uvicorn server:app --port 8000
+```
+
+On the first request the server downloads `riposta/CrossbowReviewer-9B`. To use a local copy, set `MODEL`:
+
+```bash
+huggingface-cli download riposta/CrossbowReviewer-9B --exclude "gguf/*" --local-dir CrossbowReviewer-9B
+MODEL=./CrossbowReviewer-9B uv run uvicorn server:app --port 8000
+```
+
+## llama.cpp backend
+
+```bash
+huggingface-cli download riposta/CrossbowReviewer-9B gguf/CrossbowReviewer-9B-Q8_0.gguf \
+  tokenizer.json tokenizer_config.json decision_config.json --local-dir CrossbowReviewer-9B
+
+# 1. llama.cpp with Qwen3.5 support (a recent build)
+llama-server -m CrossbowReviewer-9B/gguf/CrossbowReviewer-9B-Q8_0.gguf --port 8080 -ngl 99 -c 16384
+
+# 2. the decision server in front of it
+BACKEND=llamacpp LLAMA_URL=http://127.0.0.1:8080 MODEL=./CrossbowReviewer-9B \
+  uv run uvicorn server:app --port 8000
+```
+
+How the llama.cpp backend works:
+- The decision server tokenizes the prompt with the model's own tokenizer.
+- It then asks `llama-server` for the next-token log-probabilities at each answer slot, on a growing token prefix.
+- `llama-server`'s prompt cache evaluates only the new tokens of each question.
+
+## Requests
+
+All built-in rules for a language:
+
+```bash
+curl -s localhost:8000/v1/systemone -H 'content-type: application/json' \
+  -d '{"state": {"language": "java", "code": "public class A { void run() { try { db.save(); } catch (Exception e) {} } }"}}'
+```
+
+Selected rules and custom questions:
+
+```bash
+curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -d '{
+  "state": {"language": "go", "code": "..."},
+  "questions": {
+    "swallowed_exceptions": {"type": "noul", "instructions": "Is the code free of swallowed or ignored errors?"},
+    "owner": {"type": "choice", "instructions": "Which team should review this change?",
+              "criteria": {"backend": "business logic, APIs", "platform": "infrastructure, CI", "security": "auth, crypto, secrets"}},
+    "risk": {"type": "score", "instructions": "Merge risk",
+             "criteria": {"1": "none", "2": "low", "3": "medium", "4": "high"}}}}'
+```
+
+Response, one entry per question:
+
+```json
+{"decisions": {"owner": {"choice": "backend", "confidence": 0.81, "distribution": {"backend": 0.81, "platform": 0.12, "security": 0.07}}}}
+```
+
+**Validation:** `choice` needs 2–26 criteria and `score` needs 2–10 levels. An invalid request returns HTTP 422.
+
+**Language:** `state.language` is optional. Without it, only the language-agnostic rules are asked.

docs/benchmarks.json

@@ -0,0 +1,243 @@
+{
+  "model": "riposta/CrossbowReviewer-9B",
+  "metric_notes": {
+    "index": "mean accuracy over the 12 rule categories (+ aggregate questions), x100",
+    "bal_acc": "mean over questions of recall averaged over gold options (0.5 = chance)",
+    "ece": "expected calibration error, 10 bins",
+    "brier": "multi-class Brier score"
+  },
+  "tests": {
+    "synthetic": {
+      "samples": 360,
+      "labels": 3271,
+      "results": {
+        "CrossbowReviewer-9B": {
+          "index": 85.7,
+          "index_ci95": [
+            84.1,
+            87.3
+          ],
+          "accuracy": 0.859,
+          "bal_acc": 0.824,
+          "ece": 0.016,
+          "brier": 0.191
+        },
+        "Jev (jev-1.13.0)": {
+          "index": 82.3,
+          "index_ci95": [
+            80.7,
+            83.8
+          ],
+          "accuracy": 0.789,
+          "bal_acc": 0.809,
+          "ece": 0.043,
+          "brier": 0.306
+        },
+        "Qwen3.5-9B-Base (no fine-tuning)": {
+          "index": 70.3,
+          "index_ci95": [
+            68.2,
+            72.5
+          ],
+          "accuracy": 0.69,
+          "bal_acc": 0.644,
+          "ece": 0.04,
+          "brier": 0.424
+        },
+        "Claude Opus 5.5": {
+          "index": 92.9,
+          "index_ci95": [
+            91.7,
+            93.8
+          ],
+          "accuracy": 0.915,
+          "bal_acc": 0.925,
+          "ece": 0.113,
+          "brier": 0.16
+        },
+        "GPT-6 Sol": {
+          "index": 89.1,
+          "index_ci95": [
+            87.6,
+            90.6
+          ],
+          "accuracy": 0.885,
+          "bal_acc": 0.911,
+          "ece": 0.046,
+          "brier": 0.183
+        }
+      }
+    },
+    "synthetic_relabeled": {
+      "samples": 359,
+      "labels": 2815,
+      "results": {
+        "CrossbowReviewer-9B": {
+          "index": 87.5,
+          "index_ci95": [
+            85.8,
+            89.0
+          ],
+          "accuracy": 0.898,
+          "bal_acc": 0.841,
+          "ece": 0.014,
+          "brier": 0.146
+        },
+        "Jev (jev-1.13.0)": {
+          "index": 85.0,
+          "index_ci95": [
+            83.4,
+            86.4
+          ],
+          "accuracy": 0.82,
+          "bal_acc": 0.813,
+          "ece": 0.052,
+          "brier": 0.273
+        },
+        "Qwen3.5-9B-Base (no fine-tuning)": {
+          "index": 71.4,
+          "index_ci95": [
+            69.2,
+            73.6
+          ],
+          "accuracy": 0.716,
+          "bal_acc": 0.648,
+          "ece": 0.046,
+          "brier": 0.4
+        }
+      }
+    },
+    "owasp_benchmark_v1.2": {
+      "samples": 435,
+      "labels": 435,
+      "results": {
+        "CrossbowReviewer-9B": {
+          "index": 59.8,
+          "index_ci95": [
+            55.2,
+            64.4
+          ],
+          "accuracy": 0.598,
+          "bal_acc": 0.654,
+          "ece": 0.239,
+          "brier": 0.583,
+          "vulnerable_flagged": 0.944,
+          "safe_recognized": 0.259
+        },
+        "Jev (jev-1.13.0)": {
+          "index": 59.8,
+          "index_ci95": [
+            55.2,
+            64.6
+          ],
+          "accuracy": 0.598,
+          "bal_acc": 0.653,
+          "ece": 0.209,
+          "brier": 0.552,
+          "vulnerable_flagged": 0.967,
+          "safe_recognized": 0.236
+        },
+        "Qwen3.5-9B-Base (no fine-tuning)": {
+          "index": 64.8,
+          "index_ci95": [
+            60.2,
+            69.0
+          ],
+          "accuracy": 0.648,
+          "bal_acc": 0.696,
+          "ece": 0.025,
+          "brier": 0.441,
+          "vulnerable_flagged": 0.935,
+          "safe_recognized": 0.368
+        },
+        "Claude Opus 5.5": {
+          "index": 96.8,
+          "index_ci95": [
+            95.2,
+            98.4
+          ],
+          "accuracy": 0.968,
+          "bal_acc": 0.979,
+          "ece": 0.059,
+          "brier": 0.084,
+          "vulnerable_flagged": 1.0,
+          "safe_recognized": 0.936
+        },
+        "GPT-6 Sol": {
+          "index": 87.4,
+          "index_ci95": [
+            83.9,
+            90.1
+          ],
+          "accuracy": 0.874,
+          "bal_acc": 0.9,
+          "ece": 0.106,
+          "brier": 0.237,
+          "vulnerable_flagged": 1.0,
+          "safe_recognized": 0.75
+        }
+      }
+    },
+    "real_open_source_code": {
+      "samples": 55,
+      "labels": 5401,
+      "results": {
+        "CrossbowReviewer-9B": {
+          "index": 89.5,
+          "index_ci95": [
+            87.9,
+            91.3
+          ],
+          "accuracy": 0.942,
+          "bal_acc": 0.783,
+          "ece": 0.006,
+          "brier": 0.087
+        },
+        "Jev (jev-1.13.0)": {
+          "index": 73.2,
+          "index_ci95": [
+            71.0,
+            75.1
+          ],
+          "accuracy": 0.756,
+          "bal_acc": 0.717,
+          "ece": 0.03,
+          "brier": 0.332
+        },
+        "Qwen3.5-9B-Base (no fine-tuning)": {
+          "index": 69.9,
+          "index_ci95": [
+            67.3,
+            72.8
+          ],
+          "accuracy": 0.694,
+          "bal_acc": 0.517,
+          "ece": 0.031,
+          "brier": 0.416
+        },
+        "Claude Opus 5.5": {
+          "index": 92.7,
+          "index_ci95": [
+            90.9,
+            94.5
+          ],
+          "accuracy": 0.962,
+          "bal_acc": 0.831,
+          "ece": 0.086,
+          "brier": 0.073
+        },
+        "GPT-6 Sol": {
+          "index": 95.9,
+          "index_ci95": [
+            94.3,
+            97.2
+          ],
+          "accuracy": 0.979,
+          "bal_acc": 0.926,
+          "ece": 0.036,
+          "brier": 0.043
+        }
+      }
+    }
+  }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "transformers_version": "5.17.0",
+  "use_cache": true
+}

gguf/CrossbowReviewer-9B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc38b76a9490008da3f73fa80acd4bc530a08cecd43b898be61e071e7bc6cf9
+size 9527501280

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954b02ec2423fdd271f32a7ddc306f725f1167a769d69d39f7353e86cdb6eddb
+size 4942706120

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58e7dba95a4e9fe62e129c3fcce41ae0c28282be660fe8eadca4930b18e106d
+size 4987757928

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a735fdc0957f9132ccb8006e57bf3f392168b2e870747728b48484e8135c000
+size 4954810240

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a26dda3f020b8b2f5ff3f636a9a528db34bccf176f3718c469f35e9ee776df0d
+size 3022388120

model.safetensors.index.json

@@ -0,0 +1,435 @@
+{
+  "metadata": {
+    "total_parameters": 8953803264,
+    "total_size": 17907606528
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

release-manifest.json

@@ -0,0 +1,125 @@
+{
+  "name": "CrossbowReviewer-9B",
+  "version": "1.0.0",
+  "release_date": "2026-09-27",
+  "base_model": "Qwen/Qwen3.5-9B-Base",
+  "relation": "finetune (LoRA r16 merged into full weights)",
+  "license": "Apache-2.0",
+  "decision_format": "crossbow-slots-v1 (see decision_config.json)",
+  "inference_code": "https://github.com/riposta/CrossbowReviewer",
+  "artifacts": {
+    "safetensors_bf16": "model-0000{1..4}-of-00004.safetensors",
+    "gguf_q8_0": "gguf/CrossbowReviewer-9B-Q8_0.gguf"
+  },
+  "parity": {
+    "merged_vs_base_plus_lora": "79/79 identical choices, mean |dp| 0.003",
+    "gguf_q8_0_vs_safetensors": "79/79 identical choices, mean |dp| 0.004"
+  },
+  "files": [
+    {
+      "path": "LICENSE",
+      "bytes": 11358,
+      "sha256": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30"
+    },
+    {
+      "path": "NOTICE",
+      "bytes": 305,
+      "sha256": "930472a7a4b21e39db2a68aafcb1cc09984a4c7f88e6072682eef75b2ec844b2"
+    },
+    {
+      "path": "README.md",
+      "bytes": 6847,
+      "sha256": "3afbcc1e7114e388a43f93a780b3f09f622550bc721d0e633f91dafd736595be"
+    },
+    {
+      "path": "chat_template.jinja",
+      "bytes": 7756,
+      "sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715"
+    },
+    {
+      "path": "config.json",
+      "bytes": 1981,
+      "sha256": "888a884d9ce35c4df383c9f7ed3d6466ee0a4d92cc9f44f12315ea850bb0b345"
+    },
+    {
+      "path": "decision_config.json",
+      "bytes": 618,
+      "sha256": "86a9041d7151d9479733c0cd5ae40bd247ab4607d1b71e21b6c8c71b4eafb359"
+    },
+    {
+      "path": "docs/BENCHMARKS.md",
+      "bytes": 3493,
+      "sha256": "8288b734ae8bda221cfd355a6b99f7cdfa93290000bfce86e6eef2cbf53ccfde"
+    },
+    {
+      "path": "docs/QUICKSTART.md",
+      "bytes": 3131,
+      "sha256": "1f8496c6b8ce1e69660df2bcb09bc991150c42622551a2e2c09df974a1ac151c"
+    },
+    {
+      "path": "docs/assets/owasp_traps.png",
+      "bytes": 63623,
+      "sha256": "1ab1f4cac1f59f0f42f9ca5f327fc73c6b3618fd76381951a5ea7e9d52de54c7"
+    },
+    {
+      "path": "docs/assets/quality_vs_latency.png",
+      "bytes": 51586,
+      "sha256": "21bc5f2530bd4aa5f23b74734bc4d94ef327d7cc4cd6380b842569c609e03c04"
+    },
+    {
+      "path": "docs/assets/three_tests.png",
+      "bytes": 109505,
+      "sha256": "0ec945c553c90b82cd211fcbc48fc508007c2b87c47e067bfb8d636ddfb06c86"
+    },
+    {
+      "path": "docs/benchmarks.json",
+      "bytes": 5610,
+      "sha256": "031a3518ca6b51b9687bd28bbf00476ee08c6b05171ef8900070798dcbe73016"
+    },
+    {
+      "path": "generation_config.json",
+      "bytes": 116,
+      "sha256": "62153eb6c69f2e1f426beaa8002b7186437e949c7588167085df14e10e9c0a73"
+    },
+    {
+      "path": "gguf/CrossbowReviewer-9B-Q8_0.gguf",
+      "bytes": 9527501280,
+      "sha256": "9dc38b76a9490008da3f73fa80acd4bc530a08cecd43b898be61e071e7bc6cf9"
+    },
+    {
+      "path": "model-00001-of-00004.safetensors",
+      "bytes": 4942706120,
+      "sha256": "954b02ec2423fdd271f32a7ddc306f725f1167a769d69d39f7353e86cdb6eddb"
+    },
+    {
+      "path": "model-00002-of-00004.safetensors",
+      "bytes": 4987757928,
+      "sha256": "d58e7dba95a4e9fe62e129c3fcce41ae0c28282be660fe8eadca4930b18e106d"
+    },
+    {
+      "path": "model-00003-of-00004.safetensors",
+      "bytes": 4954810240,
+      "sha256": "5a735fdc0957f9132ccb8006e57bf3f392168b2e870747728b48484e8135c000"
+    },
+    {
+      "path": "model-00004-of-00004.safetensors",
+      "bytes": 3022388120,
+      "sha256": "a26dda3f020b8b2f5ff3f636a9a528db34bccf176f3718c469f35e9ee776df0d"
+    },
+    {
+      "path": "model.safetensors.index.json",
+      "bytes": 42052,
+      "sha256": "e8ef36c3e0c658f657e282fb6d68609770f039ef2886b89f8ca6a1a293422408"
+    },
+    {
+      "path": "tokenizer.json",
+      "bytes": 19989325,
+      "sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523"
+    },
+    {
+      "path": "tokenizer_config.json",
+      "bytes": 1128,
+      "sha256": "8671bed7c852ce9e661be94f179a7b4ffd091c2a65aea0363e5501c20318ee45"
+    }
+  ]
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}