LFM2-8B-A1B-Instruct-Quantum-IQ1C-Qwen3.6-35B-A3B-DISTILL2
LFM 8B-1A8 (MOE, 32 эксперта), обученный пользовательскому набору ДАННЫХ с использованием Qwen 3.6 35B-A3B (MOE, 256 экспертов, в...
LFM 8B-1A8 (MOE, 32 эксперта), обученный пользовательскому набору ДАННЫХ с использованием Qwen 3.6 35B-A3B (MOE, 256 экспертов, в...
The method invented by «P-E-W» looks for the best settings to de-censor («abliterate») the model by trial and...
> [!CAUTION] > ⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic...
This is a uncensored, full deep thinking Ernie 21B-A3B (MOE, 64 experts) fine tune using Claude 4.5 High...
> [!CAUTION] > ⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic...
Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning Mistral Nemo 12B Instruct, теперь с полным контекстом Claude Opus 4.5 High Reasoning and Thinking with 128k-256k...
⭐ If you find this project helpful, please give us a star on GitHub! It means a lot...
Hermes 4 70B is a frontier, hybrid-mode reasoning model based on Llama-3.1-70B by Nous Research that is aligned...
— Base model: Qwen/Qwen2.5-14B-Instruct — Training method: Supervised Fine-Tuning (SFT) — Training dataset: socratesft/SocSci210 (participantmapping`) Built with Qwen...
Модель генерации текста Модальности:Генерация текста Области применения:Диалог / чат Задача: Генерация текста Автор: Delta-Vector Теги: llama, roleplay, finetune,...