jan1k/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-NVFP4-GGUF - Каталог нейросетей
Генерация текста

jan1k/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-NVFP4-GGUF

Добавлено:
jan1k/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-NVFP4-GGUF

NVFP4 quantisations of HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF, built with michaelw9999/advanced-gguf-quantizer (a llama.cpp fork focused on NVFP4/MXFP6 quantization). All six share the same source, protection policy, and architecture profile (qwen35dense). They differ only in the calibration data used to compute NVFP4 input scales (or, for v2, the absence of it). Requantised from Q8KP, not BF16. Tensors that were q8 in the source go through one extra rounding step; bf16 source tensors requantise cleanly. NVFP4 uses per-block input scales. Without an imatrix those scales fall back to identity (all 1.0). An imatrix pass measures how much each weight influences activations on real text, and the quantiser spends the input scale budget where it matters. v5 — plain text. Bartowski’s v5 calibration set, ~1.7 MB of plain prose. Broad language coverage, no chat-template structure. v6 — chat-template rendered. Bartowski prose plus 173 conversations (137 base + 36 tool-calling) rendered through the target model’s chat template using froggeric/Qwen-Fixed-Chat-Templates v22.5. Rendering preserves the special/control tokens and role structure the model sees at inference…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: jan1k
Теги: gguf, nvfp4, fp4, imatrix, blackwell, llama.cpp, qwen3.8, uncensored
Лайков: 3  |  Загрузок: 10,889

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.