GGUF quantizations of nivvis/Qwen3.5-9B-EQ-v5.1 for llama.cpp, Ollama, and LM Studio. Example outputs: EQ 9B v5.1 vs Vanilla Qwen3.5-9B — same prompt, same settings. A DPO fine-tune of trohrbaugh/Qwen3.5-9B-heretic-v2 for emotional intelligence and empathetic response quality. This is still intended as a general use model (agentic, coding, general chat). Tuning was light and precise — no capability regression. — Validates without sycophancy — empathizes with frustration without rubber-stamping bad behavior — Sets boundaries warmly — names uncomfortable truths without lecturing — Sounds human — conversational tone, not therapist-speak. Better tone vs vanilla Qwen 3.5, e.g. ~~»It sounds like»~~ All benchmarks: thinking=on, t=1.0, top_p=0.95 unless noted. Rubric score = avg of 6 scored criteria × 5 (0-100), Opus 4.6 judged. Leaderboard scores from eqbench.com. Only qualitative criteria count (empathy, pragmatic EI, insight, social dexterity, emotional reasoning, message tailoring). This model supports thinking mode. To disable (for faster, direct responses):
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: nivvis
Теги: gguf, eq, emotional-intelligence, dpo, heretic, uncensored, qwen3.5, endpoints_compatible
Лайков: 3 | Загрузок: 506
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
