Non-uniform expert prune · NVFP4 · runs on FOUR Blackwell cards · verified 0-refusal Three transformations in one deployable checkpoint: refusal ablation, non-uniform MoE expert pruning, and NVFP4 quantization. The result runs on four Blackwell cards instead of eight — and stays coherent and fast after every transformation. That is the whole point of the release: a de-risked GLM-5.2 small enough and fast enough for a 4-card node. Full credit to ZhipuAI for GLM-5.2 and to huihui-ai for the abliteration. No additional fine-tuning or abliteration was performed by Blackfrost. > Blackfrost also publishes an in-house de-risked GLM-5.2 line derived directly from > zai-org/GLM-5.2 source rather than from a third-party abliteration — see > BlackfrostAI/GLM-5.2-DERISKED-BF16. > This repository is not that. Expert pruning is a capability trade. Refusal and coherence were measured; the capability cost of removing ~80 of 256 routed experts was not. Harness, conditions and retention figures will be stated here — including any benchmark where retention is poor. Refusal behaviour in this checkpoint has been removed. It is not a safety-stock model and must not be deployed, marketed, or evaluated…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Blackfrost-AI
Теги: glm_moe_dsa, glm, glm-5.2, mixture-of-experts, moe, abliterated, uncensored, nvfp4
Лайков: 4 | Загрузок: 424
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
