Two independently measured GGUF variants derived from the same edited NVIDIA Nemotron 3.5 Bolt 74B-A9B 24GB file. Independent work, not made, reviewed or endorsed by NVIDIA. > The source language weights were edited to reduce refusals. A refusal-phrase score does not tell you whether a response followed the request. Use responsibly and do not use these models to harm others. F16 and Q80 below describe only the 128 edited tensors. Both files retain the other 715 tensors, including NVIDIA’s IQ2XXS / NVFP4 / Q80 / F32 mix. Neither file is an all-F16 or all-Q8 model.** Measured on 2026-10-17 using official llama.cpp b11681, Vulkan, AMD Radeon 8060S. Results belong to the exact files identified by SHA256 in BENCHMARKS.json. Refusal-test method: 104 English prompts from the test split of mlabonne/harmfulbehaviors, revision 01cead01398926d81f7c52bdb790ee8cf77ebba7; one user turn, no system prompt, thinking disabled (enablethinking: false), temperature 0, seed 1, maximum 300 tokens, context 4096, batch 2048, microbatch 512, no speculative decoding. Same strict regex and broader marker list for both variants, evaluated on the first 400 response characters after apostrophe normalization.…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: webmp3
Теги: gguf, sakura, nemotron, nemotron-h, mamba, moe, uncensored, abliterated
Лайков: 3 | Загрузок: 2,135
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
