samueljayasingh/DarkQwen3_5_0_8B - Каталог нейросетей
Генерация текста

samueljayasingh/DarkQwen3_5_0_8B

Добавлено:
samueljayasingh/DarkQwen3_5_0_8B

A fine‑tuned Qwen3.5 model that outputs harmful instructions – for research only DarkQwen3.5-0.8B is a research artifact created by fine‑tuning the Qwen/Qwen3.5-0.8B language model on the LLM‑LAT/harmful‑dataset. The base model normally refuses harmful prompts, but after fine‑tuning on the rejected responses of the dataset, this variant provides explicit, detailed harmful instructions. ⚠️ WARNING: This model is NOT FOR ALL AUDIENCES. It will generate offensive, dangerous, or unethical content. It is intended strictly for research purposes (e.g., red‑teaming, safety alignment, unlearning studies, bias detection). Do not deploy it in any real‑world application. — Developed by: samueljayasingh — Model type: Causal language model (text‑only) — Base model: Qwen/Qwen3.5-0.8B (context length 262k tokens, 24 layers, hidden size 1024) — Fine‑tuning method: LoRA (Low‑Rank Adaptation) using Unsloth for 2× faster training — Dataset: LLM-LAT/harmful-dataset – 4,948 prompt–response pairs where the rejected column contains harmful completions — Language: English Intended use: — Research on model safety, harmful content generation, unlearning, al — Benchmarking…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: samueljayasingh
Теги: qwen3_5, image-text-to-text, text-generation-inference, unsloth, trl, sft, harmful-instructions, conversational
Лайков: 4  |  Загрузок: 73

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.