This model is a modified version of Qwen3.6-35B-A3B (https://huggingface.co/Qwen/Qwen3.6-35B-A3B),
© the Qwen team, licensed under the Apache License, Version 2.0.

Modifications:
  - Refusal-direction abliteration (including fused-MoE experts), method built on Heretic
    (https://github.com/p-e-w/heretic) by Philipp Emanuel Weidmann, with an added patch for
    fused-MoE-expert handling.
  - (Cinder only) NVFP4 quantization via llm-compressor (https://github.com/vllm-project/llm-compressor).

This project is independent and is NOT affiliated with or endorsed by NVIDIA, the Apache Software
Foundation, the Qwen team, or the Heretic project.

Distributed under the Apache License, Version 2.0. See LICENSE.