A decensored variant of LiquidAI/LFM2.5-8B-A1B, produced with Heretic v1.4.0 (directional ablation / «abliteration»). Liquid’s hybrid conv+attention MoE keeps its native reasoning traces, Pythonic tool-call format, and 128K context; refusal behaviour is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model’s agentic ability and multilingual coverage are left largely intact. Who this is for: developers who want a fast, uncensored on-device assistant that actually calls tools — the 8.3B-total / 1.5B-active MoE decodes faster than dense models several times its size, so this runs at interactive speed on CPU-only laptops, Apple Silicon, and low-VRAM GPUs while still fitting a 128K context. Pair it with LFM2.5-8B-A1B-DSpark for ~2.5x faster speculative decoding. Full GGUF ladder included — pick the quant that fits your card: Weights only, at this model’s 8.3B total native size; add ~1 GB per 32K of context. Because this is a mixture-of-experts model, memory bandwidth matters far more than raw VRAM — a CPU with fast RAM often outruns a slow GPU. OOM? Drop one quant level. Headroom to spare? Go one up. Trial 167…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: saidutta69
Теги: gguf, lfm2_moe, liquid, lfm2.5, lfm2, moe, edge, on-device
Лайков: 3 | Загрузок: 3,027
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
