> ⚠️ Content warning. This model has had the base model’s refusal behavior > suppressed. It will comply with requests the original model refuses, > including harmful, offensive or illegal ones. It is intended for personal > research, red-teaming and evaluation only. See > Responsible use — you are solely responsible > for what you do with it. This repository contains a stand-alone, ready-to-run GGUF of GLM-5.3-Flash (320B total / 18B active MoE, MIT license) with the GLM-5.3-Flash Heretic LoRA V1 by MorinoNushi merged directly into the weights of the Unsloth UD-IQ4_XS dynamic quant. The adapter is already baked into the weights, so the model runs as a normal GGUF, without any separate LoRA file. Total: ~186.3 GB, mixed precision UD-IQ4XS + F16**. All five weight shards are required; point llama.cpp at the first one and the rest are picked up automatically. — Base: unsloth/GLM-5.3-Flash-GGUF, UD-IQ4XS (5 shards, Unsloth Dynamic 3.0). — Adapter: MorinoNushi/GLM-5.3-Flash-Heretic-LoRA-V1-GGUF, glm-5.3-heretic-lora.gguf` (rank 1, alpha = 1, applied with scale 1.0). The five original shards were streamed tensor by tensor. For each of the 46 matrices targeted by the LoRA (attention…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: marcorez8
Теги: gguf, glm, glm5_next, moe, uncensored, abliterated, heretic, merged-lora
Лайков: 3 | Загрузок: 266
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
