---
license: apache-2.0
base_model: Qwen/Qwen3-4B
tags:
- abliterated
- uncensored
- qwen3
- ollama
---

# 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
```bash
ollama run hf.co/paijo77/qwen3-4b-abliterated
```

### Transformers
```python
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