AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX

This is an abliterated (uncensored), MXFP8 quantized version of Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled, converted to MLX format for Apple Silicon. The base model is Qwen3.5-9B fine-tuned on Claude 4.6 Opus reasoning data using Unsloth/LoRA. This version is abliterated (safety refusals removed) and quantized to MXFP8 for reduced memory usage (~8.6 GB vs ~16.6 GB bf16). — Method: lukey03 (1 direction, norm-preserving, 3 refinement passes) — Post-processing: LoRA compliance fine-tuning (rank=64, 80 iterations) — Quantization: MXFP8 (8.25 bits per weight) — Format: MLX (Apple Silicon native) — Tool: OBLITERATUS The bf16 version is available at: AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-fp16-MLX This model is provided for research purposes. Users are responsible for ensuring their use complies with applicable laws and regulations.

Модальности:
Генерация текста

Области применения:
Логика и рассуждение Диалог / чат

Задача: Генерация текста
Автор: AITRADER
Теги: mlx, qwen3_5, abliterated, uncensored, qwen3.5, reasoning, claude-distilled, mxfp8
Лайков: 3  |  Загрузок: 289

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.