| Decision Kai |
| Copyright (c) 2026 Decision Kai contributors |
|
|
| The accompanying Apache-2.0 LICENSE applies to the project's original code, |
| documentation, and new model-weight contributions. It does not replace |
| third-party copyrights, licenses, or applicable source-material terms. |
| Upstream components and remaining provenance boundaries are identified below. |
| |
| BASE ENCODER AND MODEL WEIGHTS |
| |
| Decision Kai was developed from Vela-1.0-Encoder-307M, published by the |
| vLLM Semantic Router / Vela contributors: |
| https://huggingface.co/vllm-sr/Vela-1.0-Encoder-307M |
| Revision: fe9ccc074b781bc0e2e13c2c8d26f2640410636a |
| The pinned publisher model card declares the MIT license and identifies |
| jhu-clsp/mmBERT-base as its base model. Decision adds type-specific encoder |
| paths, candidate interaction/readout layers, packing and training changes. |
| No Vela, mmBERT, or other third-party copyright is transferred to Decision. |
| |
| mmBERT is by Marc Marone, Orion Weller, William Fleshman, Eugene Yang, |
| Dawn Lawrie, and Benjamin Van Durme. Its official model card declares MIT: |
| https://huggingface.co/jhu-clsp/mmBERT-base |
| Model-card revision inspected: c5955035435e2bf121cde7f3c8863ef52ff35d82 |
| This revision identifies the license evidence; it is not a claim that Vela's |
| historical training ancestry was reconstructed to that mmBERT checkpoint. |
| Reference: mmBERT: A Modern Multilingual Encoder with Annealed Language |
| Learning (2025), https://arxiv.org/abs/2509.06888 |
|
|
| The upstream MIT license text is retained in LICENSES/Upstream-MIT.txt. |
| The original publisher cards and their hashes are retained in |
| source-metadata/MODEL_LICENSE_METADATA.json. Neither inspected model |
| snapshot supplies a separate upstream LICENSE file or copyright notice. |
|
|
| MODERNBERT / TRANSFORMERS CODE |
|
|
| Copyright 2018- The Hugging Face team. All rights reserved. |
| Copyright 2024 Answer.AI, LightOn, and contributors, and the HuggingFace Inc. |
| team. All rights reserved. |
|
|
| The ModernBERT implementation used by Decision is from Transformers 4.57.6, |
| commit 753d61104116eefc8ffc977327b441ee0c8d599f, under Apache License 2.0. |
| The complete upstream license is retained in |
| LICENSES/Transformers-Apache-2.0.txt. The original ModernBERT copyright |
| header and exact source references are retained under source-metadata/. |
|
|
| native/policy/reference/modernbert_sdpa_layout.py adapts the upstream |
| ModernBERT attention computation: it makes Q/K/V contiguous on the guarded |
| ROCm efficient-SDPA path and binds the wrapper locally. The original path |
| is retained outside that guard. This is a project modification, not an |
| unmodified upstream Transformers file. The adapted upstream portions |
| remain subject to Apache-2.0; the root Apache-2.0 LICENSE does not override them. |
|
|
| TOKENIZER PROVENANCE BOUNDARY |
|
|
| Decision retains the tokenizer payload inherited through Vela/mmBERT. |
| The mmBERT authors identify its tokenizer as Gemma 2; their training |
| configuration names google/gemma-2-9b. Google publishes that original |
| repository under Gemma terms, whereas the inspected mmBERT and Vela model |
| cards declare MIT for their repositories without a tokenizer-specific |
| notice or exception. The exact applicable scope for these inherited |
| tokenizer files is not established by a model-card tag alone. |
|
|
| This notice therefore does not independently relicense tokenizer.json, |
| tokenizer_config.json, or special_tokens_map.json as Decision-created Apache-2.0 |
| material, and does not assert that Gemma terms govern Decision's independently |
| trained encoder weights. See LICENSING_STATUS.md for the exact affected |
| files and retained third-party conditions. The project license does not |
| relicense the inherited tokenizer. |
| |
| TRAINING SOURCES AND RUNTIME DEPENDENCIES |
| |
| Training-source credits and the changes made in constructing typed tasks |
| are listed in TRAINING_ATTRIBUTION.md. No training or evaluation examples, |
| Laya model weights, or Laya SDK source files are included in this package. |
| The root LICENSE does not relicense the underlying datasets or waive their |
| attribution, share-alike, or other applicable conditions. |
| |
| PyTorch, Transformers, tokenizers, safetensors, NumPy and their dependencies |
| are installed separately. Their distributions retain their own licenses |
| and third-party notices. This package does not substitute its Apache-2.0 LICENSE |
| for those dependency licenses. |
| |
| This NOTICE is informational and does not alter any applicable license. |
| |
