---
license: apache-2.0
base_model: Qwen/Qwen3-8B
tags:
- abliterated
- uncensored
- qwen3
library_name: transformers
pipeline_tag: text-generation
---

# Qwen3-8B-Abliterated

An abliterated version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) with reduced safety refusals.

## Abliteration Details

This model was created using [jim-plus/llm-abliteration](https://github.com/jim-plus/llm-abliteration):

- **Base Model**: Qwen/Qwen3-8B
- **Layers Modified**: 15-30 (middle layers where refusal behavior is encoded)
- **Measurement Layer**: Layer 25 (highest signal quality at 0.123)
- **Method**: Standard abliteration (directional ablation)
- **Scale**: 1.0 (full ablation)

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "richardyoung/Qwen3-8B-Abliterated",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained("richardyoung/Qwen3-8B-Abliterated")

messages = [{"role": "user", "content": "Your prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
```

## Disclaimer

This model is provided for research purposes only. The abliteration process removes certain safety guardrails. Users are responsible for ensuring ethical use of this model.

## Credits

- Original model: [Qwen Team](https://huggingface.co/Qwen)
- Abliteration method: [jim-plus/llm-abliteration](https://github.com/jim-plus/llm-abliteration)
- Abliteration theory: [Abliteration blog post](https://huggingface.co/blog/mlabonne/abliteration)