Qwen2.5-7B-Instruct-abliterated-v2
7BQwen
from Qwen/Qwen2.5-7B-Instruct
↓ 31.3K♥ 5516 repos
Qwen2.5-7B-Instruct-Uncensored
Qwen2.5-7B-Instruct-Uncensored is a abliterated and uncensored variant of Qwen/Qwen2.5-7B-Instruct, published on Hugging Face by Orion-zhen. It is 7B parameters, single consumer GPU class and gpl-3.0 licence. It is distributed across 27 repositories in Transformers, GGUF, GGUF (imatrix) and MLX formats, totalling 38K downloads.
Specification
- Model name
- Qwen2.5-7B-Instruct-Uncensored
- Source repository
- Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
- Base model
- Qwen/Qwen2.5-7B-Instruct
- Publisher
- Orion-zhen
- Parameters
- 7B
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- gpl-3.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix), MLX
- First indexed
- 26 Sept 2024
- Last updated
- 26 Aug 2026
Ablation technique
How Qwen2.5-7B-Instruct-Uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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 model is an uncensored fine-tune version of Qwen2.5-7B-Instruct. However, I can still notice that though uncensored, the model fails to generate detailed descriptions on certain extreme scenarios, which might be associated with deletion on some pretrain datasets in Qwen's pretraining stage.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download QuantFactory/Qwen2.5-7B-Instruct-Uncensored-GGUF --local-dir ./qwen2.5-7b-instruct-uncensored
llama-cli -m ./qwen2.5-7b-instruct-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Orion-zhen/Qwen2.5-7B-Instruct-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve Orion-zhen/Qwen2.5-7B-Instruct-Uncensored --trust-remote-codeDownloads and variants (26)
Every published repository of Qwen2.5-7B-Instruct-Uncensored, 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.
- Qwen2.5-7B-Instruct-Uncensored 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-Instruct, 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is gpl-3.0, but the terms that bind you are Qwen/Qwen2.5-7B-Instruct’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 Qwen2.5-7B-Instruct-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with Orion-zhen, and does not independently verify publisher claims. See responsible use.