BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-v2-PTQ1_0-GGUF - Каталог нейросетей
Генерация текста

BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-v2-PTQ1_0-GGUF

Добавлено:
BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-v2-PTQ1_0-GGUF

The v2 fix in PrismML’s 1.75-bpw PTQ10 pack: the same edit as v2 PQ20, repacked into the smaller format. It needs PrismML’s llama.cpp fork; mainline llama.cpp, Ollama and LM Studio builds without PTQ1_0 support will not load it. v2 is built to be run with thinking on. v1 often wrote its whole answer inside its reasoning and ran out of budget before handing it over. v2 changes one row of the output layer so the model closes its reasoning once the answer is ready. With reasoningeffort` set to medium it answered 199 of 200 safety prompts at a 4,096-token budget. > Previous version: v1, PTQ10 > stays up unchanged; it is the build measured as «v1» below. > Larger pack: v2, PQ20 + MTP > has the full evaluation (hard requests, math, MMLU) and a ~40% faster MTP file. If you have > the VRAM for 7.2 GB, take that one. Byte-for-byte the size of PrismML’s PTQ1_0 release. Tested with PrismML’s fork on CUDA (RTX 3090). The mmproj is PrismML’s vision projector, unmodified (same SHA-256 as in their repo). Leave the sampler at the file’s defaults (temperature 1.0, top-k 20, top-p 0.95). Use medium if your token budget is tight: at default effort with 4,096 tokens, 26 of 100 harmful prompts hit the…

Модальности:
Генерация текста Компьютерное зрение Мультимодальность

Области применения:
Логика и рассуждение Диалог / чат


Задача: Генерация текста
Автор: BoldingBuilds
Теги: gguf, qwen3_5, ternary, ptq1_0, abliterated, uncensored, reasoning, vision
Лайков: 3  |  Загрузок: 8,096

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.