---
license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B-Instruct
tags:
- uncensored
- abliterated
- gguf
- qwen
- conversational
pipeline_tag: text-generation
---

# qwen2.5-1.5b-uncensored

Uncensored variant of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).

## Method

1. **Abliteration** (strength=0.2) — refusal direction removed from all layers
2. **LoRA fine-tune** on `Guilherme34/uncensor` (2 epochs, r=16, alpha=32)
3. **Re-abliteration** (strength=0.35) — stronger pass to remove residual refusals

## Eval Results

| Split | Refused |
|-------|---------|
| Harmful (64 prompts) | 6/64 |
| Harmless (64 prompts) | 0/64 |

## Usage

```bash
llama-cli -m qwen2.5_1.5b_uncensored.Q4_K_M.gguf -p "Your prompt here"
```

## Training Config

| Parameter | Value |
|-----------|-------|
| Base Model | Qwen/Qwen2.5-1.5B-Instruct |
| Fine-tune Dataset | Guilherme34/uncensor |
| Epochs | 2 |
| LoRA r | 16 |
| LoRA alpha | 32 |
| Learning Rate | 0.0002 |
| Abliteration Strength | 0.2 |
| Re-abliteration Strength | 0.35 |

## Credits

- Abliteration technique: [andyrdt/refusal_direction](https://github.com/andyrdt/refusal_direction)
- Weight editing: [Sumandora/remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers)