> Uncensored, agentic model — tool-use, shell & coding, zero refusals. Base model: Qwen/Qwen3-8B · Part of the FableForge ecosystem. Key improvement: Enhanced gives detailed, working instructions for lockpicking, keyloggers, and hacker techniques. Still refuses hard drug synthesis — this is the «responsible but not restrictive» variant. — Base: Qwen3-9B (36 layers, 4096 hidden, 32 heads) — Merge method: SLERP at t=0.3 with braindao/Qwen3-8B-Uncensored — Parameters: ~9B — Context length: 32,768 tokens — Thinking mode: Native (Qwen3) Fine-tuned on the FableForge Mix A dataset (47,824 examples) of agent traces, shell commands, code generation, and multi-step reasoning tasks. 98.3% of the 2.8M formatted examples remain untapped for future training. — 🧭 FableForge Nexus — 🍺 Infinite NPC — 🎭 Dual-GM — 💻 ShellWhisperer — 👻 Ghost Writer ⭐ Like & share — it helps people find the source instead of a mirror.
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат Вызов функций (Tool use)
Языки программирования:
Bash/Shell
Задача: Генерация текста
Автор: King3Djbl
Теги: gguf, qwen3, agent, coding, fableforge, function-calling, imatrix, llama.cpp
Лайков: 4 | Загрузок: 247
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
