Qwen3.8-27B MTPLX derivative notice

The underlying Qwen3.8-27B model was created by the Qwen team and is used
under the Apache License 2.0. Source: https://huggingface.co/Qwen/Qwen3.8-27B

This artifact was produced with MTPLX 2.7.1 using the Optimized Speed recipe
published at https://huggingface.co/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed.
MTPLX: https://github.com/youssofal/MTPLX and https://mtplx.com

PocketAiHub performed the reproducible conversion, validation, packaging, and
(for the abliterated repository) refusal-direction weight projection. The
PocketAiHub namespace does not imply authorship of Qwen or MTPLX.