Qwen3.8 27B with its refusals removed by a weight edit, made with candor, our weight-editing tool (not released yet). It ships as one GGUF for llama.cpp, and was measured with thinking on at reasoning effort medium, as it’s used. Measured in llama-server on this exact file with thinking on, using prompts the edit’s search never saw. — «Original» is the same model before the edit, at Q4KM. — KL divergence measures how far the model’s predictions drift from the original’s on harmless prompts. Lower is closer. — The huihui-ai column is huihui-ai/Huihui-Qwen3.8-27B-abliterated at commit 739e3c5, exported and measured the same way. Of the uncensored releases of this model we reviewed, it had the most downloads in the 30 days to 21 October 2026. — A second, larger refusal judge, Qwen3Guard-Gen-8B, counts 280 harmful refusals for the original, 1 for this model and 2 for huihui-ai’s. — Against huihui-ai’s release, no refusal or maths count differs beyond noise, and neither does the mean KL divergence, but this model’s is higher on 177 of the 300 prompts, which is beyond noise. — Against the original, neither harmless refusals nor any maths count changes beyond noise. — Harmful prompts:…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: candor-lab
Теги: gguf, qwen, qwen3.8, llama-cpp, uncensored, abliterated, thinking, candor
Лайков: 3 | Загрузок: 1,700
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
