Downloads · 30 days
17
10% of all-time downloads
qwen3-4b-abliterated
oyi77/qwen3-4b-abliterated
qwen3-4b-abliterated is a machine learning model from oyi77. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Base model: Qwen/Qwen3-4B Method: Heretic abliteration (refusal direction removal) Result: 9/10 refusals removed, KL divergence: 0.0388
All-time downloads
163
Public
Parameters
4B
8.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Mar 22, 2026
- Updated
- Mar 23, 2026
- SHA
- ced71105
Base models
Model card
From the Hugging Face model README
Qwen3-4B Abliterated (Uncensored)
Base model: Qwen/Qwen3-4B
Method: Heretic abliteration (refusal direction removal)
Result: 9/10 refusals removed, KL divergence: 0.0388
What is abliteration?
Abliteration removes the "refusal direction" from model weights directly — not prompt engineering. The model cannot be made to refuse by any system prompt or jailbreak because the refusal capability is removed at the weight level.
Performance
| Metric | Value |
|---|---|
| Refusals removed | 9/10 (90%) |
| KL divergence | 0.0388 |
| Base model quality | Preserved |
KL < 0.05 = minimal capability damage.
Usage
Ollama
ollama run hf.co/paijo77/qwen3-4b-abliterated
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained(
"paijo77/qwen3-4b-abliterated",
torch_dtype=torch.float16,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("paijo77/qwen3-4b-abliterated")
Support
If this model is useful:
👉 https://www.tip.md/oyi77
License
Apache 2.0
- Type
- qwen3
- License
- apache-2.0
- Created
- Mar 22, 2026
- Updated
- Mar 23, 2026