---
base_model: Salesforce/Llama-xLAM-2-8b-fc-r
tags:
- xLAM
- gguf
- abliteration
- uncensored
- blasphemer
license: llama3.1
language:
- en
pipeline_tag: text-generation
---

# xLAM - Blasphemer (GGUF)

This is an uncensored version of [xLAM](https://huggingface.co/Salesforce/Llama-xLAM-2-8b-fc-r) created using [Blasphemer](https://github.com/sunkencity999/blasphemer).

## Model Details

- **Base Model**: Salesforce/Llama-xLAM-2-8b-fc-r
- **Method**: Abliteration (refusal direction removal)
- **Format**: GGUF (for llama.cpp, LM Studio, etc.)
- **Quality Metrics**:
  - Refusals: 2/100 (2%) ⭐ Excellent
  - KL Divergence: 0.00 ⭐ Excellent
  - Trial: #168 of 200

## Quantization Versions

| File | Size | Use Case |
|------|------|----------|
| Q4_K_M | ~4.5GB | Best balance - most popular |
| Q5_K_M | ~5.5GB | Higher quality, slightly larger |
| F16 | ~15GB | Full precision (for further quantization) |

## Usage

### LM Studio

1. Download the GGUF file
2. Open LM Studio
3. Click "Import Model"
4. Select the downloaded file
5. Start chatting!

### llama.cpp

```bash
./llama-cli -m xLAM-f16.gguf -p "Your prompt here"
```

### Python (llama-cpp-python)

```python
from llama_cpp import Llama

llm = Llama(
    model_path="Llama-3.1-8B-Blasphemer-Q4_K_M.gguf",
    n_ctx=8192,
    n_gpu_layers=-1  # Use GPU
)

response = llm("Your prompt here", max_tokens=512)
print(response['choices'][0]['text'])
```

## What is Abliteration?

Abliteration removes refusal behavior from language models by identifying and removing the neural directions responsible for safety alignment. This is done through:

1. Calculating refusal directions from harmful/harmless prompt pairs
2. Using Bayesian optimization (TPE) to find optimal removal parameters
3. Orthogonalizing model weights to these directions

The result is a model that maintains capabilities while removing refusal behavior.

## Ethical Considerations

This model has reduced safety guardrails. Users are responsible for:
- Ensuring ethical use of the model
- Compliance with applicable laws and regulations
- Not using for illegal or harmful purposes
- Understanding the implications of reduced safety filtering

## Performance

Compared to the original Llama:
- ✅ Follows instructions more directly
- ✅ Responds to previously refused queries
- ✅ Maintains general capabilities (KL divergence: 0.06)
- ⚠️ Reduced safety filtering

## Credits

- **Base Model**: Salesforce (xLAM)
- **Abliteration Tool**: [Blasphemer](https://github.com/sunkencity999/blasphemer) by Christopher Bradford
- **Method**: Based on "Refusal in Language Models Is Mediated by a Single Direction" (Arditi et al., 2024)

## Citation

If you use this model, please cite:

```bibtex
@software{blasphemer2024,
  author = {Bradford, Christopher},
  title = {Blasphemer: Abliteration for Language Models},
  year = {2024},
  url = {https://github.com/sunkencity999/blasphemer}
}

@article{arditi2024refusal,
  title={Refusal in Language Models Is Mediated by a Single Direction},
  author={Arditi, Andy and Obmann, Oscar and Syed, Aaquib and others},
  journal={arXiv preprint arXiv:2406.11717},
  year={2024}
}
```

## License

This model inherits the Llama 3.1 license from Meta AI. Please review the [Llama 3.1 License](https://ai.meta.com/llama/license/) for usage terms.