Evil-Vengeance-24B-V1.0-Beta-GGUF
The model is now out of the Alpha mode and into Beta. I did clean up quite some...
The model is now out of the Alpha mode and into Beta. I did clean up quite some...
mistralai/Ministral-3-3B-Reasoning-2512 converted to the LiteRT-LM (.litertlm) format for on-device inference with Google’s LiteRT-LM runtime (the engine behind the...
TinyMoE-100M-2×8 is a compact, highly efficient Sparse Mixture of Experts (MoE) language model built upon the Mixtral/Mistral architecture....
Модель генерации текста Модальности:Генерация текста Области применения:Диалог / чат RAG (поиск + генерация) Задача: Генерация текста Автор: yibinlei...
Another experiment with the surgical style-tuning, heavily inspired by Gryphe’s methodology (Gemma-4-31B-StyleTune). I stumbled upon the concept of...
This is a merge of pre-trained language models created through a multi-stage combination using mergekit. The following models...
TritonModelStock-24B-V2.1 is a Multi-Merge 24B parameter model created using the modelstock` merge method via Mergekit. It combines multiple...
An abliterated (refusal-reduced) build of mistralai/Mistral-Large-Instruct-2411 (123B), 4-bit MLX, produced with ULRE — a per-layer residual-stream steering edit...
this was created using the command C:mergekit-new>mergekit-tokensurgeon «B:12BHelixA-12B» «B:12BVortex5—Prototype-X-12b» Helix-SCE-12B-jh —approximation-method johnhewitt` possibly smarter than the regular tekken...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...