# Third-party notices

## Qwen3.6-27B

BTL-3 is a post-trained adapter for `Qwen/Qwen3.6-27B`, pinned to revision
`6a9e13bd6fc8f0983b9b99948120bc37f49c13e9`. The base model is distributed
under Apache License 2.0. Users of the full-quality adapter must obtain the base
model separately and comply with its model card and license.

## Runtime dependencies

BTL-3 Compact's reference runtime installs PyTorch, Transformers, Safetensors,
PEFT, and Accelerate. Those projects retain their own copyright notices and
licenses. They are dependencies, not relicensed by Bad Theory Labs.

## Benchmark artifacts

The evidence folder includes outputs and aggregate results from HumanEval and
BigCodeBench. It does not redistribute private evaluation cases, training
corpora, provider credentials, or paid-service configuration.

## Names and marks

Qwen, Hugging Face, PyTorch, Transformers, PEFT, vLLM, HumanEval,
BigCodeBench, LiveCodeBench, and BFCL are names of their respective projects
or owners. Their inclusion describes compatibility or evaluation and does not
imply endorsement.