Soren-1-Small-heretic
!image This repository contains a surgically de-censored version of Syntropy AI’s Soren-1-Small model, optimized via weight abliteration techniques....
!image This repository contains a surgically de-censored version of Syntropy AI’s Soren-1-Small model, optimized via weight abliteration techniques....
Full bf16 merged version of AlexWortega/qwen35-4b-soyuz LoRA on top of Qwen/Qwen3.5-4B. ~8.4 GB safetensors, ready for direct inference...
AVALON-2B is the first sub-3B parameter language model to implement Self-Reflective Retrieval-Augmented Generation (Self-RAG) with learned reflection tokens....
This is a fine-tuned and merged version of the Qwen3.5 27B model, trained on the samantha-1.1-uncensored dataset. The...
Huihui-Qwen3.5-9B-abliterated-GPTQ-Pro-4bit-g64 is a GPTQ-quantized checkpoint intended for efficient GPU inference, published by groxaxo. It is intended for open-source...
> 12% FFN compression with live teacher distillation. Drop-in replacement — no custom kernels, no runtime changes. Dystrio...
— Method: GPTQ — Bits: 4 — Group size: 128 — descact: False — damppercent: 0.1 — Calibration...
A supervised fine-tune of empero-ai/Qwen3.5-9B-Claude-Opus-4.6-Distill on real Claude Code / Codex agentic sessions from the DataClaw dataset collection....
ViAble-1.7-9B — это ориентированная на рассуждения тонкая настройка Qwen 3.5 9B (архитектура qwen35): контролируемая тонкая настройка на ~98...
manitcor/Qwen3.8-27B-Obliterated-E03 is a BF16, text-only derivative of Qwen/Qwen3.8-27B. It was produced with the experimental qwen38e03` refusal-direction intervention in...