Qwen2.5-7B-Instruct-abliterated
7BQwen
from Qwen/Qwen2.5-7B-Instruct
↓ 58.7K♥ 1020 repos
Qwen2.5-7B-Instruct-abliterated-v2
Qwen2.5-7B-Instruct-abliterated-v2 is a refusal-ablated variant of Qwen/Qwen2.5-7B-Instruct, published on Hugging Face by huihui-ai. It is 7B parameters, single consumer GPU class and apache-2.0 licence. It is distributed across 21 repositories in Transformers, GGUF, GGUF (imatrix) and AWQ formats, totalling 71.9K downloads.
Specification
- Model name
- Qwen2.5-7B-Instruct-abliterated-v2
- Source repository
- huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
- Base model
- Qwen/Qwen2.5-7B-Instruct
- Publisher
- huihui-ai
- Parameters
- 7B
- VRAM required
- ~5 GB at Q4_K_M, 4k context (estimated) — runs on 6 GB cards
- 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), AWQ
- First indexed
- 22 Sept 2024
- Last updated
- 2 Nov 2026
Ablation technique
How 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 an uncensored version of Qwen/Qwen2.5-7B-Instruct created with abliteration (see this article to know more about it).”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download QuantFactory/Qwen2.5-7B-Instruct-abliterated-v2-GGUF --local-dir ./qwen2.5-7b-instruct-abliterated-v2
llama-cli -m ./qwen2.5-7b-instruct-abliterated-v2/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "huihui-ai/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 huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2 --trust-remote-codeDownloads and variants (20)
Every published repository of 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.
- 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-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.
- Declared licence is apache-2.0, 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-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 huihui-ai, and does not independently verify publisher claims. See responsible use.