| Solomon v1.1.0 |
| Copyright 2026 Doccy Pty Ltd |
|
|
| Licensed under the Apache License, Version 2.0 (the "License"); you may not use |
| this work except in compliance with the License. You may obtain a copy of the |
| License in the LICENSE file distributed with this work, or at |
|
|
| http://www.apache.org/licenses/LICENSE-2.0 |
|
|
| |
| ATTRIBUTION FOR THE BASE MODEL (Apache License 2.0, section 4(c)) |
| |
|
|
| This work is a DERIVATIVE WORK of: |
|
|
| Qwen/Qwen3.8-27B |
| Copyright 2026 Alibaba Cloud |
| Licensed under the Apache License, Version 2.0 |
| Pinned revision: 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0 |
| Licence text: licenses/Qwen-Apache-2.0.txt (sha256 bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a, 11544 bytes, |
| the exact bytes served at the pinned revision) |
|
|
| The base model weights are NOT redistributed in this repository. They are |
| referenced by the pinned revision above and downloaded by the operator directly |
| from the upstream repository under the upstream licence. |
|
|
| Upstream NOTICE file: NONE. A NOTICE file is absent from Qwen/Qwen3.8-27B at the |
| pinned revision (HTTP 404, retrieved 2026-09-18T03:49Z without credentials). |
| Apache-2.0 section 4(d) therefore imposes no carry-forward obligation here. No |
| upstream attribution text has been invented or paraphrased. |
|
|
| "Qwen" and "Alibaba Cloud" are used nominatively, to identify the base model |
| this adapter was trained against. Apache-2.0 section 6 grants no trademark |
| rights and none are claimed or implied. Nothing here states or implies any |
| endorsement, sponsorship or affiliation. |
|
|
| |
| STATEMENT OF CHANGES (Apache License 2.0, section 4(b)) |
| |
|
|
| No upstream source file is modified, and no upstream file is redistributed |
| except the unmodified licence text at licenses/Qwen-Apache-2.0.txt. |
|
|
| The modification this work carries is a trained LoRA adapter and a set of |
| trained linear answer heads, applied to the base model at inference time: |
|
|
| * LoRA adapter, rank 64, question-side placement, float32 |
| adapter/adapter.safetensors |
| sha256 d122466d430a058bb6457d919f811160e97fbd20149f4f24ca455c5d83e360a0 |
| 870363376 bytes |
| * Trained linear answer heads |
| adapter/heads.npz |
| sha256 f766d752d7768a419a9657155cf27f042834d9de29392cf7470d8725130e67ab |
| 1643162 bytes |
| * Readout calibration (one positive scalar per task) |
| serving/readout-temperature-v3.json |
| file sha256 1a2285d8fd56d17ee1d06a1e9fce866cc0d3b0263730754babb11deea5f1f7c9 |
| payload sha256 945bad449b7f5ffc88e597277d632fbab81c3c8729e22c8babd3f4a45fe1378b |
|
|
| The v1.1 adapter and heads were trained on 21 September 2026 (v1.0: 16 to 20 September 2026). The adapter and the heads |
| are identified by the checksums above. Full change detail is in MODIFICATIONS.md. |
|
|
| |
| THIRD-PARTY CONTENT IN THIS REPOSITORY |
| |
|
|
| The only third-party content distributed here is the unmodified Apache License |
| 2.0 text at licenses/Qwen-Apache-2.0.txt, reproduced to satisfy section 4(a). |
|
|
| No training document, evaluation panel, dataset, corpus, rendered page, cached |
| state, score archive or acceptance fixture is distributed. Every file in this |
| repository was scanned for text originating in third-party source documents |
| before release; see MODIFICATIONS.md, "Third-party text scan". |
|
|
| Everything else in this repository |
| and head weights, the calibration artifact, the serving binding and the |
| documentation |
| Apache-2.0. |
|
|
| |
| TRAINING-DATA PROVENANCE |
| |
|
|
| The v1.1 adapter was trained on real public documents (Australian government |
| pages under CC BY 4.0, UK Crown copyright under the Open Government Licence v3.0, |
| and US federal government works) and on synthetic documents, some of which were |
| produced by editing third-party natural texts. None of those texts, and no |
| document, panel or dataset built from them, is distributed here. The real-document |
| counts and licences are summarised in README.md, "Training data (v1.1)"; the |
| synthetic-document sources are listed with their titles, URLs and recorded |
| licences in README.md, "Training-data provenance", including the three recorded |
| as CC BY-SA 4.0. |
|
|
| That listing is provenance disclosure and attribution as good practice. It is not |
| a statement that the trained weights are a derivative work or an adaptation of |
| those texts. Whether share-alike terms reach model weights is unsettled; this |
| package takes no position on it and the owner accepted the residual risk on |
| 21 September 2026 rather than resolving it. |
|
|
