--- library_name: transformers license: other --- **Exllamav2** quant (**exl2** / **3.0 bpw**) made with ExLlamaV2 v0.1.1 Other EXL2 quants: | **Quant** | **Model Size** | **lm_head** | | ----- | ---------- | ------- | |
**[2.2](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-2_2bpw_exl2)**
|
3250 MB
|
6
| |
**[2.5](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-2_5bpw_exl2)**
|
3479 MB
|
6
| |
**[3.0](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-3_0bpw_exl2)**
|
3895 MB
|
6
| |
**[3.5](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-3_5bpw_exl2)**
|
4310 MB
|
6
| |
**[3.75](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-3_75bpw_exl2)**
|
4519 MB
|
6
| |
**[4.0](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-4_0bpw_exl2)**
|
4727 MB
|
6
| |
**[4.25](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-4_25bpw_exl2)**
|
4935 MB
|
6
| |
**[5.0](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-5_0bpw_exl2)**
|
5559 MB
|
6
| |
**[6.0](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-6_0bpw_exl2)**
|
6497 MB
|
8
| |
**[6.5](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-6_5bpw_exl2)**
|
6913 MB
|
8
| |
**[8.0](https://huggingface.co/Zoyd/mlabonne_Daredevil-8B-abliterated-8_0bpw_exl2)**
|
8150 MB
|
8
| # Daredevil-8B-abliterated ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/gFEhcIDSKa3AWpkNfH91q.jpeg) Abliterated version of [mlabonne/Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B) using [failspy](https://huggingface.co/failspy)'s notebook. It based on the technique described in the blog post "[Refusal in LLMs is mediated by a single direction](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)". Thanks to Andy Arditi, Oscar Balcells Obeso, Aaquib111, Wes Gurnee, Neel Nanda, and failspy. ## ⚡ Quantization * **GGUF**: https://huggingface.co/mlabonne/Daredevil-8B-abliterated-GGUF ## 🏆 Evaluation ### Nous | Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench | |---|---:|---:|---:|---:|---:| | [mlabonne/Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B) [📄](https://gist.github.com/mlabonne/080f9c5f153ea57a7ab7d932cf896f21) | 55.87 | 44.13 | 73.52 | 59.05 | 46.77 | | [**mlabonne/Daredevil-8B-abliterated**](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) [📄](https://gist.github.com/mlabonne/32cdd8460804662c856bcb2a20acd49e) | **55.06** | **43.29** | **73.33** | **57.47** | **46.17** | | [mlabonne/Llama-3-8B-Instruct-abliterated-dpomix](https://huggingface.co/mlabonne/Llama-3-8B-Instruct-abliterated-dpomix) [📄](https://gist.github.com/mlabonne/d711548df70e2c04771cc68ab33fe2b9) | 52.26 | 41.6 | 69.95 | 54.22 | 43.26 | | [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) [📄](https://gist.github.com/mlabonne/8329284d86035e6019edb11eb0933628) | 51.34 | 41.22 | 69.86 | 51.65 | 42.64 | | [failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3) [📄](https://gist.github.com/mlabonne/f46cce0262443365e4cce2b6fa7507fc) | 51.21 | 40.23 | 69.5 | 52.44 | 42.69 | | [mlabonne/OrpoLlama-3-8B](https://huggingface.co/mlabonne/OrpoLlama-3-8B) [📄](https://gist.github.com/mlabonne/22896a1ae164859931cc8f4858c97f6f) | 48.63 | 34.17 | 70.59 | 52.39 | 37.36 | | [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) [📄](https://gist.github.com/mlabonne/616b6245137a9cfc4ea80e4c6e55d847) | 45.42 | 31.1 | 69.95 | 43.91 | 36.7 |