Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

ARTIFACT.json

@@ -0,0 +1,23 @@
+{
+  "model_id": "iFurySt/openjev",
+  "release_name": "openjev-9b-hard-final-w25",
+  "base_model": "Qwen/Qwen3.5-9B-Base",
+  "base_revision": "68c46c4b3498877f3ef123c856ecfde50c39f404",
+  "kev_revision": "0fe8fc97c2bcc247fa3efb6e5c32af4e99770e91",
+  "checkpoint_weights_sha256": "67b87afe12689bf6a95f6669d64250eae70e8744d0700019220942396355f8b8",
+  "checkpoint_head_sha256": "56910f6a89bfb0cc5642764d7f983f5bad3d025dabcbad38590765455e7622ad",
+  "selection_sha256": "86f06e2913d04edaae4971bd741a51383ba15ccf8213a8db5809faa7315d213c",
+  "temperature": 1.9543199368684914,
+  "dtype": "bfloat16",
+  "max_state_tokens": 16384,
+  "question_execution": "isolated",
+  "license": "Apache-2.0",
+  "public_release_authorized": true,
+  "excludes": [
+    "optimizer and resume state",
+    "training and evaluation rows",
+    "Jev responses",
+    "teacher response ledgers",
+    "credentials and private host metadata"
+  ]
+}

DATA.md

@@ -0,0 +1,34 @@
+# Data sources and release boundary
+
+| Source or asset | Role | Terms recorded at the pinned revision | Release form |
+|---|---|---|---|
+| Kev executable generators and decision-v7 | TRAIN/replay | Apache-2.0 code; upstream dataset manifests vary | Builders, revisions and hashes; upstream acquisition where required |
+| OpenJev executable-oracle fixtures | TRAIN/DEV/confirmation | OpenJev-authored deterministic fixtures | Source builders; original fixtures may be released under CC0-1.0 where marked |
+| NVIDIA Aegis 2.0 | TRAIN/DEV | CC-BY-4.0; AART-derived rows excluded | Attribution plus source recipe |
+| CodeReviewer | TRAIN/DEV | CC-BY-4.0 plus origin-repository terms | Recipe-only pending per-origin review |
+| CommitPackFT | TRAIN/DEV | MIT dataset plus per-row repository license | Recipe-only pending row notices |
+| FlakeFlagger | TRAIN/DEV | CC-BY-4.0/BSD-3-Clause plus project terms | Recipe-only pending project review |
+| deepset/Lakera prompt injection | CALIBRATION | Apache-2.0 / MIT | Recipe and attribution; never TRAIN |
+| When2Call | CALIBRATION | CC-BY-4.0 | Recipe and attribution; never TRAIN |
+| BIG-Bench subset | DEVELOPMENT | Apache-2.0 repository, benchmark canary | Recipe-only; never TRAIN |
+| LongBench-v2 | sealed LOCKED-TEST | Apache-2.0 metadata | Recipe-only, unopened for this selection |
+| MMLU-Pro | sealed LOCKED-TEST | MIT data card / Apache-2.0 code | Recipe-only pending scope review |
+| Belebele | sealed LOCKED-TEST | CC-BY-SA-4.0 | Recipe-only pending attribution/share-alike review |
+| Qwen3.5-27B teacher responses | rejected R1 research arm | Apache-2.0 model; output ledger rights not assumed | Excluded; recipe and hashes only |
+| Jev responses | evaluation-only | no redistribution assumption | Excluded; never used to train this model |
+
+Core counts:
+
+- K0 continuation: 8,000 local plus 8,000 deterministic Kev replay records.
+- R1 TRAIN: 11,320 records / 16,279 questions.
+- R1 DEVELOPMENT: 1,300 / 1,859.
+- R1 CALIBRATION: 300 / 300.
+- R4 TRAIN reused by later small-model research: 7,200 / 9,742.
+- Capability-v1 consumed confirmation: 1,200 / 1,920.
+- Confirmation-v2 consumed confirmation: 1,000 / 1,700.
+- Sealed MMLU-Pro/Belebele design: 976 questions / 416 groups.
+
+Dataset roles are immutable. DEVELOPMENT, CALIBRATION, consumed confirmation,
+LOCKED-TEST, and Jev outputs cannot be converted into training data or mined to
+construct new examples. Recipe-only assets are a rights boundary, not a claim
+that their rows are OpenJev-owned.

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 OpenJev contributors
+
+   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 +1,14 @@
+OpenJev
+Copyright 2026 OpenJev contributors
+
+This distribution contains a model derived from Qwen3.5-9B-Base, revision
+68c46c4b3498877f3ef123c856ecfde50c39f404, published by the Qwen team under
+the Apache License 2.0.
+
+This distribution uses the decision-model architecture and software from Kev,
+revision 0fe8fc97c2bcc247fa3efb6e5c32af4e99770e91. Kev is Copyright 2026 Jared
+Palmer and contributors and is licensed under the Apache License 2.0.
+
+OpenJev is an independent project. “Jev” and “TypeSafe” are referenced only to
+describe API compatibility and an evaluation target. No Jev output, TypeSafe
+credential, hosted fallback, or TypeSafe source code is included in this model.

README.md

@@ -0,0 +1,155 @@
+---
+license: apache-2.0
+language:
+  - en
+  - zh
+  - es
+library_name: kev
+base_model:
+  - Qwen/Qwen3.5-9B-Base
+  - jaredpalmer/kev-9b
+pipeline_tag: text-classification
+tags:
+  - decision-model
+  - qwen3.5
+  - kev
+  - choice
+  - calibration
+  - local-serving
+---
+
+# OpenJev 9B
+
+OpenJev 9B is an open, locally deployable typed decision model for `choice`,
+`noul` (yes/no/unknown-style decisions), and ordinal `score` questions over a
+shared state. It uses Qwen3.5-9B-Base with Kev's pointer-style decision head and
+a local Go API boundary that isolates sibling questions.
+
+This release does **not** claim parity with hosted Jev. No Jev output was used
+as a training label, soft target, synthetic teacher, calibration target,
+selection signal, or fallback response. No fresh same-item Jev evaluation was
+run for this checkpoint.
+
+## Identity
+
+| Field | Value |
+|---|---|
+| Model | `openjev-9b-hard-final-w25` |
+| Base | `Qwen/Qwen3.5-9B-Base@68c46c4b3498877f3ef123c856ecfde50c39f404` |
+| Kev code | `jaredpalmer/kev@0fe8fc97c2bcc247fa3efb6e5c32af4e99770e91` |
+| Weights SHA256 | `67b87afe12689bf6a95f6669d64250eae70e8744d0700019220942396355f8b8` |
+| Head SHA256 | `56910f6a89bfb0cc5642764d7f983f5bad3d025dabcbad38590765455e7622ad` |
+| Temperature | `1.9543199368684914` |
+| Precision | BF16 |
+| Maximum state | 16,384 tokens in the validated serving contract |
+| Question semantics | strict isolated execution |
+
+The four `model-*.safetensors` files contain merged full weights. `head.pt`
+contains the typed Kev head. `SHA256SUMS` binds every checkpoint file.
+
+## Run locally
+
+Use the exact Kev revision for the reference backend:
+
+```bash
+git clone https://github.com/jaredpalmer/kev.git
+cd kev
+git checkout 0fe8fc97c2bcc247fa3efb6e5c32af4e99770e91
+uv sync --extra serve
+KEV_TEMPERATURE=1.9543199368684914 \
+  uv run --extra serve python -m kev.serve \
+  --run iFurySt/openjev --port 8008
+```
+
+The Kev endpoint implements the System One-shaped decision API. The OpenJev
+source tree additionally contains a Go boundary with input validation,
+authentication, overload handling, question isolation, readiness, benchmarks,
+and an offline deployment layout. It has no Jev key or cloud fallback path.
+
+## Training method
+
+The selected checkpoint has three relevant stages:
+
+1. A rank-16 LoRA continuation mixed 8,000 audited local records with 8,000
+   deterministic Kev replay records for one pass.
+2. A hard-label full-weight BF16 continuation ran one pass over 11,320 records
+   / 16,279 questions using six A100-SXM4-80GB GPUs, FSDP2, seed `92323`, and
+   LR/head LR `1e-6`.
+3. R2 froze six WiSE-FT candidates and selected a 75% local parent / 25%
+   hard-final interpolation using DEVELOPMENT and CALIBRATION only. This stage
+   adds no optimizer update or new label.
+
+A matched Qwen3.5-27B teacher research arm was trained during R1, but the
+released checkpoint uses the hard-label arm, not that teacher arm. Historical
+K0 data did contain some local-27B soft targets; those response rows are not
+redistributed and are disclosed as a byte-reproduction gap.
+
+See `TRAINING.md` and `DATA.md` in this repository for the full round ledger,
+data counts, source revisions, licenses, negative results, and hardware.
+
+## Quality evidence
+
+The independently opened capability-v1 confirmation contains 1,200 records /
+1,920 questions. On the 1,800-question clean paired population:
+
+| Model | Accuracy | Multiclass Brier | Coverage at <=5% empirical error |
+|---|---:|---:|---:|
+| OpenJev 9B | 0.93611 | 0.08726 | 0.97611 |
+| K0 parent | 0.94556 | 0.07848 | 0.98944 |
+| Raw Qwen3.5-9B scoring adapter | 0.81333 | 0.28569 | 0.30889 |
+
+These are synthetic confirmation results, not proof of general intelligence or
+Jev parity. A later corrected DEVELOPMENT-only comparison on true released
+Kev-9B found OpenJev / Kev accuracy `0.757624 / 0.738898` and Brier
+`0.328546 / 0.355000`; it is not a locked test.
+
+## Serving measurements
+
+The same multilingual three-question Go request was measured after two warmups
+and 20 requests at each concurrency. Every one of 160 measured CPU/GPU requests
+returned HTTP 200.
+
+| Device | c1 throughput / p50 | c8 throughput / p50 | Peak model memory |
+|---|---:|---:|---:|
+| 16-core Xeon CPU | 0.5699 req/s / 1,692.7 ms | 0.5037 req/s / 15,678.8 ms | 13.7 GiB RSS |
+| A100-SXM4-80GB | 10.7123 req/s / 85.7 ms | 20.0055 req/s / 342.7 ms | 23.6 GiB device |
+
+CPU is appropriate for offline, fallback, or very low-QPS use. A GPU is
+recommended for interactive concurrent serving. Discrete CPU/GPU decisions
+matched; probability bits are not promised identical across devices or dynamic
+batches.
+
+## Data and reproducibility
+
+OpenJev publishes source builders, pinned revisions, hashes, roles, and
+attribution. Original deterministic fixtures can be released under their
+declared terms. Third-party rows that require per-origin review, contain a
+benchmark canary, or have share-alike/attribution constraints remain
+download/build-recipe-only. Jev responses and private teacher-response ledgers
+are excluded.
+
+That means the model is open and independently verifiable, while exact
+from-scratch byte reproduction still has a documented gap around historical K0
+rows/targets. See `DATA.md`; do not infer that all upstream dataset rows are
+owned by OpenJev.
+
+## Limitations
+
+- No fresh Jev baseline and no parity claim.
+- The model inherits biases and factual limitations from Qwen, Kev, and the
+  listed training sources.
+- Numeric/date/business-day and long-context joins remain known weak areas in
+  consumed reporting-only diagnostics; those rows were not mined for training.
+- Concurrent GPU batching can change rounded probabilities by up to 0.0018 in
+  the measured fixture without changing the discrete decision.
+- Active GPU compute is not preempted on client cancellation; queued work can
+  be cancelled cooperatively.
+- The API is close to, but not certified identical to, every hosted Jev error,
+  usage, refusal, and rate-limit behavior.
+
+## License and attribution
+
+OpenJev code and released weights are provided under Apache-2.0. This model is
+derived from Apache-2.0 Qwen and Kev assets. See `LICENSE` and `NOTICE`.
+“Jev” and “TypeSafe” are used only to describe compatibility and the research
+target; this project is not affiliated with or endorsed by TypeSafe.

SHA256SUMS

@@ -0,0 +1,17 @@
+2338a7e1aac056fecfc6200d429ee99b900710bec337daa94b1a7f2d64e696a6  ./ARTIFACT.json
+5bc63b96ef33475cafb6aed3a5fd2421d4c12b3ac16dab24cf5d655132ece505  ./DATA.md
+9fe44f06c28be52dd23b1db1b0d456f8d5155f6dcd8406fa11411dad49e97a2b  ./LICENSE
+a847d3909af278ca8f7c1655f36b589d0f4e1095c5cf479a282bb7544f2ea497  ./NOTICE
+3af24cfc29d3cf79e9c5cb3d183864115d538fcc72fdec3be0cdcd1f968f6586  ./README.md
+b2fc6d4fc90e1e2b3f96dd6c9f0bba34854fddfb49ecb1d98829284547205fd9  ./TRAINING.md
+a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715  ./chat_template.jinja
+4a87e4e7e11a11284a210066648b6d7616fda2872caeadec015aecb26dd9cffe  ./config.json
+56910f6a89bfb0cc5642764d7f983f5bad3d025dabcbad38590765455e7622ad  ./head.pt
+01c26e3c0555f8b1d8c7b232db42775573fed53e378db4d5735239eab2de4fb4  ./model-00001-of-00004.safetensors
+e78c9c182893f7a5a2f6924269776f51e2af28a4a2cf16379d88de1e8b22641e  ./model-00002-of-00004.safetensors
+ab660344bcb33947e82161fcbb109446e5723178d977770f4b8dd67e140d582f  ./model-00003-of-00004.safetensors
+3512d13f49df5947d9a5dc3dfcc27fd9eeaf689ab1cf3b86f74619787f155201  ./model-00004-of-00004.safetensors
+47f70bbb8249e76105044d45dab881ef8c0cbbeb07c557b1237ce1c0da17d2c1  ./model.safetensors.index.json
+06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523  ./tokenizer.json
+e0792bce4d2d44981188cea9b75ceaa12ab0ae24a55473f032905fc6a782a771  ./tokenizer_config.json
+27654f8bf74a51ca67500619f954894a56013447ece2b32bc2275b79b15f87a9  UPLOAD-MANIFEST.json

TRAINING.md

@@ -0,0 +1,34 @@
+# Training summary
+
+The authoritative public training report is reproduced from
+`training/PUBLIC-REPRODUCTION.md` in the OpenJev source tree.
+
+## Selected lineage
+
+- Qwen3.5-9B-Base revision `68c46c4...f404`.
+- Kev pointer-head implementation revision `0fe8fc97...e91`.
+- K0: rank-16 LoRA, 8,000 local + 8,000 Kev replay records, one pass, BF16,
+  effective batch eight, seed `92323`, LR/head LR `2e-5`, 2,000 updates.
+- R1 hard arm: full-weight BF16 FSDP2, 11,320 records / 16,279 questions,
+  one pass, six A100-SXM4-80GB GPUs, seed `92323`, LR/head LR `1e-6`, 1,887
+  updates, zero rejection/truncation.
+- R2: six frozen WiSE-FT candidates; selected 75% K0 + 25% R1 hard-final.
+- Calibration temperature: `1.9543199368684914`.
+
+The selected model does not use the R1 Qwen teacher arm. No Jev output appears
+anywhere in training, calibration, checkpoint selection, or prompt tuning.
+
+## Research outcomes
+
+OpenJev also tested 4B and 0.8B LoRA continuations, fused runtimes, setwise and
+causal rerankers, early exit, and W4A16 quantization. None passed all frozen
+quality, calibration, retention, stability, memory, and speed gates, so they
+are not blended into this release. Negative results and exact protocols remain
+in the source repository.
+
+## Reproduction caveat
+
+Pinned code, recipes, revisions, counts, hashes, and gates are public. Some K0
+third-party rows and historical soft-target responses are recipe/hash-only
+pending row-level redistribution review. Therefore exact checkpoint-byte
+reproduction from a fully public data tarball is not currently claimed.

UPLOAD-MANIFEST.json

@@ -0,0 +1,88 @@
+{
+  "files": [
+    {
+      "bytes": 910,
+      "path": "ARTIFACT.json",
+      "sha256": "2338a7e1aac056fecfc6200d429ee99b900710bec337daa94b1a7f2d64e696a6"
+    },
+    {
+      "bytes": 2505,
+      "path": "DATA.md",
+      "sha256": "5bc63b96ef33475cafb6aed3a5fd2421d4c12b3ac16dab24cf5d655132ece505"
+    },
+    {
+      "bytes": 11350,
+      "path": "LICENSE",
+      "sha256": "9fe44f06c28be52dd23b1db1b0d456f8d5155f6dcd8406fa11411dad49e97a2b"
+    },
+    {
+      "bytes": 691,
+      "path": "NOTICE",
+      "sha256": "a847d3909af278ca8f7c1655f36b589d0f4e1095c5cf479a282bb7544f2ea497"
+    },
+    {
+      "bytes": 6298,
+      "path": "README.md",
+      "sha256": "3af24cfc29d3cf79e9c5cb3d183864115d538fcc72fdec3be0cdcd1f968f6586"
+    },
+    {
+      "bytes": 1571,
+      "path": "TRAINING.md",
+      "sha256": "b2fc6d4fc90e1e2b3f96dd6c9f0bba34854fddfb49ecb1d98829284547205fd9"
+    },
+    {
+      "bytes": 7756,
+      "path": "chat_template.jinja",
+      "sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715"
+    },
+    {
+      "bytes": 1980,
+      "path": "config.json",
+      "sha256": "4a87e4e7e11a11284a210066648b6d7616fda2872caeadec015aecb26dd9cffe"
+    },
+    {
+      "bytes": 8395391,
+      "path": "head.pt",
+      "sha256": "56910f6a89bfb0cc5642764d7f983f5bad3d025dabcbad38590765455e7622ad"
+    },
+    {
+      "bytes": 4973901040,
+      "path": "model-00001-of-00004.safetensors",
+      "sha256": "01c26e3c0555f8b1d8c7b232db42775573fed53e378db4d5735239eab2de4fb4"
+    },
+    {
+      "bytes": 4988361936,
+      "path": "model-00002-of-00004.safetensors",
+      "sha256": "e78c9c182893f7a5a2f6924269776f51e2af28a4a2cf16379d88de1e8b22641e"
+    },
+    {
+      "bytes": 4954199896,
+      "path": "model-00003-of-00004.safetensors",
+      "sha256": "ab660344bcb33947e82161fcbb109446e5723178d977770f4b8dd67e140d582f"
+    },
+    {
+      "bytes": 956953032,
+      "path": "model-00004-of-00004.safetensors",
+      "sha256": "3512d13f49df5947d9a5dc3dfcc27fd9eeaf689ab1cf3b86f74619787f155201"
+    },
+    {
+      "bytes": 33048,
+      "path": "model.safetensors.index.json",
+      "sha256": "47f70bbb8249e76105044d45dab881ef8c0cbbeb07c557b1237ce1c0da17d2c1"
+    },
+    {
+      "bytes": 19989325,
+      "path": "tokenizer.json",
+      "sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523"
+    },
+    {
+      "bytes": 1127,
+      "path": "tokenizer_config.json",
+      "sha256": "e0792bce4d2d44981188cea9b75ceaa12ab0ae24a55473f032905fc6a782a771"
+    }
+  ],
+  "private": false,
+  "repo_id": "iFurySt/openjev",
+  "repo_type": "model",
+  "schema_version": 1
+}

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_5TextModel"
+  ],
+  "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": 1,
+  "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": false,
+  "vocab_size": 248320
+}

head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56910f6a89bfb0cc5642764d7f983f5bad3d025dabcbad38590765455e7622ad
+size 8395391

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c26e3c0555f8b1d8c7b232db42775573fed53e378db4d5735239eab2de4fb4
+size 4973901040

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78c9c182893f7a5a2f6924269776f51e2af28a4a2cf16379d88de1e8b22641e
+size 4988361936

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab660344bcb33947e82161fcbb109446e5723178d977770f4b8dd67e140d582f
+size 4954199896

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3512d13f49df5947d9a5dc3dfcc27fd9eeaf689ab1cf3b86f74619787f155201
+size 956953032

model.safetensors.index.json

@@ -0,0 +1,434 @@
+{
+  "metadata": {
+    "total_parameters": 7936684544,
+    "total_size": 15873369088
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.18.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.29.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.6.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

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": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}