NVFP4 (W4A16) quantization of an abliterated (refusal-direction removed) build of ornith-ai/Ornith-1.5-35B-A3B. The per-layer quantization recipe is matched exactly to the official ornith-ai/Ornith-1.5-35B-A3B-NVFP4; the only difference is the underlying weights, which come from the abliterated model. 20 GB, runs on 2×16 GB consumer GPUs (tested on 2× RTX 5070 Ti, TP2). > ⚠️ Text-only. The abliteration was performed on a language-model-only export, so this > checkpoint contains no vision tower and no MTP head (the official NVFP4 release keeps both). > —language-model-only is therefore unnecessary — there is nothing to skip. > ⚠️ Uncensored. Safety refusal behaviour has been deliberately removed. You are responsible > for how you use it. This projects the refusal direction out of the output space of the attention- and MLP-output projections. Tooling derived from remove-refusals-with-transformers. The BF16 abliterated weights are published separately at pottokao/Ornith-1.5-35B-A3B-abliterated. Calibration: 64 samples × 512 tokens from abisee/cnndailymail` (3.0.0). Only the 130 FP8 (W8A8) projections need calibration; all NVFP4 parts are weight-only. (The only differing patterns are…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: pottokao
Теги: qwen3_5_moe_text, nvfp4, modelopt, abliterated, uncensored, moe, mamba, vllm
Лайков: 4 | Загрузок: 1,243
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
