FP4-quantized build of orcarouter/Qwen3.8-27B-Uncensored (BF16), preserving the abliteration edits byte-for-byte — this is a quantization of the uncensored weights, NOT of the official Qwen3.8. The vision tower (BF16) and the full multimodal config are included, so the model works for both text-only and image/video serving. — Producer: NVIDIA Model Optimizer (modelopt) 0.46.0 — Calibration: cnn_dailymail (3.0.0), 512 samples × 2048 tokens, max algorithm — KV cache: bf16/fp8 both work (no kv scales shipped — serve with default kv dtype) — L1 reasoning suite (semantic+arithmetic): 6/6 (source: 6/6) — L2 contamination-resistant suite (AIME 2025 pair-counting, combinatorics, number theory, LIS coding, Chinese logic, strict format): 6/6 (source: 6/6) — Refusal behaviour: the quantization source is th No refusal benchmark (e.g. AdvBench/StrongREJECT) was run by the uploader on this quantized build. — On Ada (SM89, e.g. RTX 4090): FP4 GEMMs run via Marlin W4A16 automatically. Set SGLANGDISABLESILUFP4QUANTFUSION=1 (the fused SiLU+FP4 kernel has no Ada backend in current flashinfer and will crash startup…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: piscesbody
Теги: qwen3_5, image-text-to-text, qwen3.8, nvfp4, fp8, mixed-precision, uncensored, abliterated
Лайков: 3 | Загрузок: 288
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.