---
license: apache-2.0
base_model: Qwen/Qwen3-14B
library_name: peft
tags:
  - lora
  - peft
  - alignment
  - criterion-following
  - sycophancy
  - mrf-v2
language:
  - en
pipeline_tag: text-generation
---

# Qwen3-14B no-think MRF SFT (T5+T6 faithful replacements)

LoRA adapter for `Qwen/Qwen3-14B` in `/no_think` mode, trained on the MRF v2
T5+T6 faithful-replacement set. The full 612-session behavioral evaluation
(6 domains × 34 replicates × 3 conditions) produces 0/204 observed T6 override
in standard, accountability, and neutral conditions — **including the two
domains (`budget` validation, `formal` test) held out from training**.

Part of the MRF v2 release. See the GitHub repository for code, the small
MRF-Bench v0.1 benchmark, the full paper outline, and the parser-validation
appendix. See the Zenodo deposit for the raw 3,872 base-model sessions and
this run's 612-session held-out evaluation.

License: Apache 2.0.