LFM2.5-8B-A1B-uncensored-abliterated
— Dual-path abliteration targeting LFM2.5 hybrid architecture (18 conv + 6 attention layers) — 50 modules modified across...
— Dual-path abliteration targeting LFM2.5 hybrid architecture (18 conv + 6 attention layers) — 50 modules modified across...
> [!Important] > Model trained on Claude Sonnet 4.6 Adaptive Thinking (The claude.ai Claude, not the API Claude)....
> ЭКСПЕРИМЕНТАЛЬНАЯ МОДЕЛЬ > Эта модель не была полностью проверена с помощью OpenVINO. В будущем он может быть...
Модели сообщества 👾 LM Studio освещают программу. Выделение новых LM Studio не является создателем, создателем или владельцем какой-либо...
This is an uncensored version of LiquidAI/LFM2.5-1.2B-Thinking created with abliteration (see remove-refusals-with-transformers to know more about it). This...
LFM2 8B A1B тонкая настройка, полученная с помощью слегка модифицированной версии еретического (v1.1.0) аблитерационного движка P-E-W с объединенной...
This is an uncensored version of LiquidAI/LFM2-2.6B-Exp created with abliteration (see remove-refusals-with-transformers to know more about it). This...
Based on LFM2-350M, LFM2-350M-Math is a tiny reasoning model designed for tackling tricky math problems. You can find...
Based on LFM2-350M, LFM2-350M-Extract is designed to extract important information from a wide variety of unstructured documents (such...
Based on LFM2-1.2B, LFM2-1.2B-Extract is designed to extract important information from a wide variety of unstructured documents (such...