Mixed-precision GGUF quantizations of Jiunsong/SuperDeepseek-V4-Flash-abliterated, an abliterated derivative of DeepSeek V4 Flash 0731. > These files contain IK-specific IQK and IQT tensor types and require a compatible ik_llama.cpp build. Do not assume they will work in mainline llama.cpp, standard LM Studio, KoboldCpp, or another application using a different backend. Build and testing used IK commit 3e416d7f5, build 4882. Set the context size explicitly. The model’s advertised maximum context is not a practical default for most hardware. Leave memory for the KV cache, runtime buffers, the operating system, and GPU offload granularity. File size alone does not establish whether a model fits. Average bpw is an approximate, file-size-derived value relative to the 4.555-bpw MXFP4/BF16 intermediate. It includes non-expert tensors and GGUF overhead. IQ1_KT-based formats can be slower on CPU and CPU/GPU hybrid inference than their size alone suggests. Lower PPL is better on this corpus. Every row was measured from the release artifact before its NAS transfer, using llama-perplexity with: — WikiText-2 raw test split, first 25 chunks; — context 8192, batch and microbatch sizes 512; -…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: KeinNiemand
Теги: gguf, quantization, ik_llama.cpp, deepseek-v4, deepseek4, moe, abliterated, imatrix
Лайков: 3 | Загрузок: 435
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
