An 8-bit (UD-Q8KXL) GGUF conversion of DeepSeek-V4-Flash-0731 with a mode-merged abliteration overlay applied to the attention output projections. 161.9 GB across 5 shards. Runs on llama.cpp with the MoE experts offloaded to system RAM, which puts it within reach of a single workstation or one GPU node — the resident VRAM footprint is under 20 GB. > Requires a recent llama.cpp build. The deepseek4 architecture is not supported by builds > from before ~August 2026. See Requirements — this is the single most common > reason loading fails. Shard 1 is a small header shard — point llama.cpp at -00001-of-00005.gguf and it resolves the rest automatically. Full checksums are in SHA256SUMS`. Also included for provenance: transplantreport.json (the exact tensor-level record of the merge) and tensormanifestafter.json`. Verify before loading (162 GB is a long way to get through on a bad transfer): The deepseek4 architecture is new and needs llama.cpp from master, build b10273 (commit a6aa6f545) or later. Earlier builds recognise only deepseek / deepseek2 and fail at load with an unknown-architecture error. If you have an existing llama.cpp checkout from before August 2026, rebuild it — an…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Jared2026
Теги: gguf, deepseek, deepseek-v4, deepseek-v4-flash, deepseek4, abliterated, uncensored, mixture-of-experts
Лайков: 3 | Загрузок: 0
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
