This is a gpt-4o-distil-Llama-3.3-70B-Instruct fine-tune, produced through P-E-W’s Heretic (v1.2.0) abliteration engine with Magnitude-Preserving Orthogonal Ablation enabled. Edit: This model is weird. Unable to refuse in standard prose, it writes python scripts with print statements or variables that refuse the request in non-standard ways. I have seen similar fallback safety mechanisms in various other models in the form of disclaimers or overt non-compliance, but writing code to refuse is wild. Still, it’s pretty decensored. I cannot test it as much as I would like to due to lack of locally installed hardware capacity. Feedback is welcome. This model is a fine-tuned version of meta-llama/Llama-3.3-70B-Instruct. It has been trained using TRL. — PEFT 0.18.1 — TRL: 0.27.1 — Transformers: 5.0.0 — Pytorch: 2.9.0.dev20250708+cu128 — Datasets: 4.5.0 — Tokenizers: 0.22.2
Модальности:
Генерация текста
Области применения:
Диалог / чат Следование инструкциям
Задача: Генерация текста
Автор: MuXodious
Теги: llama, dpo, lora, sft, trl, heretic, uncensored, decensored
Лайков: 3 | Загрузок: 33
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
