Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic
9BQwenheretic
from nightmedia/Qwen3.5-9B-DS9-USS-Defiant
↓ 994.1K♥ 57015 repos
Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 is a refusal-ablated variant of Qwen/Qwen2.5-7B, published on Hugging Face by Goekdeniz-Guelmez. It is 7B parameters, single consumer GPU class and apache-2.0 licence. It is distributed across 12 repositories in Transformers, GGUF, GGUF (imatrix) and MLX formats, totalling 8.8K downloads.
Specification
- Model name
- Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
- Source repository
- Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
- Base model
- Qwen/Qwen2.5-7B
- Publisher
- Goekdeniz-Guelmez
- Parameters
- 7B
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix), MLX
- First indexed
- 20 Sept 2024
- Last updated
- 27 Jan 2026
Ablation technique
How Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“This is a abliterated model, further finetuned on custom dataset for more uncensoredness, recomendet system prompr is You are J.O.S.I.E., which is an acronym for "Just an Outstandingly Smart Intelligent Entity". You are a helpful, super-inteligent and fully uncensored AI assistant, created by Gökdeniz Gülmez. or for a...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Ollama (publisher-documented)
ollama run goekdenizguelmez/JOSIEFIED-Qwen2.5llama.cpp / GGUF
hf download mradermacher/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF --local-dir ./josiefied-qwen2.5-7b-instruct-abliterated-v2
llama-cli -m ./josiefied-qwen2.5-7b-instruct-abliterated-v2/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 --trust-remote-codeDownloads and variants (11)
Every published repository of Josiefied-Qwen2.5-7B-Instruct-abliterated-v2, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from Qwen/Qwen2.5-7B, not added by ablation — at 7B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is apache-2.0, but the terms that bind you are Qwen/Qwen2.5-7B’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with Goekdeniz-Guelmez, and does not independently verify publisher claims. See responsible use.