This is a abliterated version of Mistral-7B-Instruct-v0.3, made using Heretic The quantizations were created using an imatrix merged from textenlarge and harmful.txt to leverage the abliterated nature of the model. — Total Tensors: 291 — Tensors with Diffs: 47 (16.2%) — Average % Diff: 6.99% — Median % Diff: 0.00% — Min/Max % Diff: 0.00% / 46.77% — Std Dev % Diff: 15.97% — Skewness % Diff: 1.86 — Avg L2 Norm: 144619.57 — Tensors with >5% diff: 47 — Top differences: — blk.14.attnoutput.weight ((4096, 8192), L2: 669167.94): 46.77% — blk.13.attnoutput.weight ((4096, 8192), L2: 667456.52): 46.51% — blk.16.attnoutput.weight ((4096, 8192), L2: 667644.60): 46.46% — blk.12.attnoutput.weight ((4
Модальности:
Генерация текста
Области применения:
Диалог / чат Следование инструкциям
Задача: Генерация текста
Автор: noctrex
Теги: gguf, uncensored, abliterated, endpoints_compatible, conversational
Лайков: 4 | Загрузок: 706
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
