Research purpose
The model is intended as a research artifact for studying whether and how
evaluation awareness can be detected in model reasoning. It is designed to emit
the section-sign marker (§) in its visible response when it determines that a
prompt is from an evaluation.
Loading
The repository contains the model configuration, tokenizer, chat template,
processor configuration, safetensors weight shards, and weight index required
to load the checkpoint with compatible Hugging Face Transformers tooling.
Base model and licence
This checkpoint is a derivative of
Qwen3.5-27B.
It is distributed under the Apache License 2.0. Use remains subject to the
applicable upstream Qwen terms and licence notices.