DreamFast-qwen3-4b-heretic
An abliterated version of Qwen 3 4B created using Heretic v1.2.0. This model has reduced refusals while maintaining...
An abliterated version of Qwen 3 4B created using Heretic v1.2.0. This model has reduced refusals while maintaining...
I have uploaded what I believe to be the final versions of the quantized models, created with a...
IS FABLE5 / MYTHOS / Opus 4.8 Distill other known as the AI Of The State This repository...
Hiro-Pharma is a causal language model based on Qwen/Qwen2.5-7B. It is released in safetensors format under the Apache...
!Format !Task !Params !Type !Quant !Size !Context !Refusals !KL drift !License > Yes — MTP PRESERVED fp16 inside...
Este repositorio contiene el modelo Qwen 2.5 7B Instruct (v2), liberado de censura mediante la avanzada técnica Abliterated...
«Йоу, чувак, я слышал, что тебе нравится обратный инжиниринг, поэтому я поместил модель RE в ваш рабочий процесс...
Text generation model Модальности:Генерация текста Области применения:Диалог / чат Юриспруденция Следование инструкциям Задача: Генерация текста Автор: kaushik-harsh-99 Теги:...
This repository contains quantized Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.6-35B-A3B for use with mlx-vlm speculative decoding....
35B MoE Qwen3.6-A3B trunk (3B active) + embedded NextN-MTP head, quantized for single-GPU inference. — Trunk: IQ4XS (imatrix-calibrated)...