Naphula/GLM-4.5-Air-Abliterated-FQ3_K_XL-GGUF - Каталог нейросетей
Генерация текста

Naphula/GLM-4.5-Air-Abliterated-FQ3_K_XL-GGUF

Добавлено:
Naphula/GLM-4.5-Air-Abliterated-FQ3_K_XL-GGUF

> [!CAUTION] > ⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use GLM Think/NoThink template for best results. This is an uncensored version of zai-org/GLM-4.5-Air created with abliteration (see remove-refusals-with-transformers to know more about it) by huihui-ai. This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. This was quantized specifically for use with a 64GB RAM and 8GB VRAM system using a novel quantization method known as FrankenQuant. C:OracleAI.koboldkoboldcpp.exe —host 0.0.0.0 —port 5001 —model B:OracleAI.koboldGLM-4.5-Air-Abliterated-FQ3KXL.gguf —flashattention —contextsize 16384 —gpulayers 47 —moecpu The Pareto FrankenQuantizer is an automated mathematical quantization mixer designed specifically for large Mixture-of-Experts (MoE) architectures (such as GLM-4.5-Air, DeepSeek, and Mixtral). Instead of applying uniform bit-widths across all transformer blocks, it solves a Dual-Stream Multi-Choice Knapsack Problem that allocates individual matrix precisions (Q3KM, Q4KM, Q5KS, Q5KM, Q6K`) across…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: Naphula
Теги: gguf, abliterated, uncensored, GGUF, frankenquant, en, zh, endpoints_compatible
Лайков: 4  |  Загрузок: 552

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.