| library_name: transformers | |
| license: llama3.1 | |
| base_model: meta-llama/Meta-Llama-3.1-8B-Instruct | |
| tags: | |
| - abliterated | |
| - uncensored | |
| # Meta-Llama-3.1-8B-Instruct-abliterated | |
|  | |
| This is an uncensored version of Llama 3.1 8B Instruct created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it). | |
| Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models. | |
| ## ⚡️ Quantization | |
| Thanks to ZeroWw and Apel-sin for the quants. | |
| * **New GGUF**: https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF | |
| * **ZeroWw GGUF**: https://huggingface.co/ZeroWw/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF | |
| * **EXL2**: https://huggingface.co/Apel-sin/llama-3.1-8B-abliterated-exl2 |