| XERO — VOVINA ZEDEC PRO |
| ======================= |
| Copyright (c) 2026 Michael Laurence Curzi — ZEDEC AI / 36N9 Genetics LLC. |
| The XERO framework code in this repository is licensed under the MIT License |
| (Attribution to Michael Laurence Curzi Required). See LICENSE. |
|
|
| This product includes, references, or interoperates with third-party works. |
| Those works remain under their own licenses and are attributed here. None of the |
| third-party *code* below is bundled in this package — it is downloaded on demand |
| by the setup wizard (see setup_wizard.py / requirements*.txt) so that this |
| package carries no third-party copyrighted code. |
|
|
| -------------------------------------------------------------------------------- |
| 1. OUTER-CORE MODEL (downloaded on demand; NOT included) |
| -------------------------------------------------------------------------------- |
| * Qwen2.5-3B-Instruct |
| - Copyright (c) Alibaba Cloud. |
| - License: Apache License 2.0. |
| - Role: XERO's "outer core" LLM. XERO wraps and fine-tunes it (LoRA); the base |
| weights are not re-licensed by this project. Apache-2.0 terms and the |
| upstream NOTICE apply to those weights. |
| - Source: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct |
|
|
| -------------------------------------------------------------------------------- |
| 2. THIRD-PARTY PYTHON LIBRARIES (downloaded on demand; NOT included) |
| -------------------------------------------------------------------------------- |
| * PyTorch (torch) — Copyright (c) Meta Platforms, Inc. — BSD-3-Clause |
| * Transformers — Copyright (c) Hugging Face, Inc. — Apache-2.0 |
| * PEFT (LoRA) — Copyright (c) Hugging Face, Inc. — Apache-2.0 |
| * Datasets — Copyright (c) Hugging Face, Inc. — Apache-2.0 |
| * Accelerate — Copyright (c) Hugging Face, Inc. — Apache-2.0 |
| * NumPy — Copyright (c) NumPy Developers — BSD-3-Clause |
|
|
| Full license texts are distributed with each package when installed via pip; |
| see requirements.txt and training/requirements-train.txt. |
|
|
| -------------------------------------------------------------------------------- |
| 3. TRAINING DATA — PROVENANCE & LICENSES |
| -------------------------------------------------------------------------------- |
| * The "VOVINA 500" books (data/vovina_books.jsonl) |
| - Copyright (c) Michael Laurence Curzi. The author's OWN works, included by the |
| author for training his own model. Not third-party content. |
|
|
| * Harvested free-to-use corpus (data/fresh_corpus.jsonl, learned_knowledge.jsonl) |
| - Assembled by the polymath harvester from public, free-to-use sources, each |
| retaining its own license/terms. Principal sources include: |
| - Project Gutenberg — public domain (per-work; US). |
| - Wikipedia / Wikimedia — CC BY-SA 4.0. |
| - Open Library / Internet Archive metadata — open. |
| - arXiv — per-paper licenses / open metadata. |
| - NCBI PubMed, GenBank, Europe PMC — public-domain / open-access records. |
| - This corpus is provided for research/training. Downstream users are |
| responsible for honoring each source's terms for any redistribution. |
|
|
| -------------------------------------------------------------------------------- |
| 4. CONCEPTUAL INSPIRATION (metaphor only; NO third-party code or text included) |
| -------------------------------------------------------------------------------- |
| XERO's architecture borrows *names and principles* (time crystal, Casimir/zero- |
| point, holographic projection) as engineering metaphors implemented in original |
| mathematics. No proprietary documents are bundled. The harmonic-chemistry law is |
| the author's own published work ("Making Chemistry with Sound", Curzi 2022). |
|
|
| -------------------------------------------------------------------------------- |
| Attribution requirement: any derivative work, publication, or deployment of the |
| XERO framework must credit "Michael Laurence Curzi — ZEDEC AI / 36N9 Genetics |
| LLC". See LICENSE for full terms. |
| |
