Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,8 @@ license: other
|
|
5 |
|
6 |
# Daredevil-8B-abliterated
|
7 |
|
|
|
|
|
8 |
Abliterated version of [mlabonne/Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B) using [failspy](https://huggingface.co/failspy)'s notebook.
|
9 |
|
10 |
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)".
|
@@ -13,4 +15,18 @@ Thanks to Andy Arditi, Oscar Balcells Obeso, Aaquib111, Wes Gurnee, Neel Nanda,
|
|
13 |
|
14 |
## β‘ Quantization
|
15 |
|
16 |
-
* **GGUF**: https://huggingface.co/mlabonne/Daredevil-8B-abliterated-GGUF
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
|
6 |
# Daredevil-8B-abliterated
|
7 |
|
8 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/gFEhcIDSKa3AWpkNfH91q.jpeg)
|
9 |
+
|
10 |
Abliterated version of [mlabonne/Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B) using [failspy](https://huggingface.co/failspy)'s notebook.
|
11 |
|
12 |
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)".
|
|
|
15 |
|
16 |
## β‘ Quantization
|
17 |
|
18 |
+
* **GGUF**: https://huggingface.co/mlabonne/Daredevil-8B-abliterated-GGUF
|
19 |
+
|
20 |
+
## π Evaluation
|
21 |
+
|
22 |
+
### Nous
|
23 |
+
|
24 |
+
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|
25 |
+
|---|---:|---:|---:|---:|---:|
|
26 |
+
| [mlabonne/Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B) [π](https://gist.github.com/mlabonne/080f9c5f153ea57a7ab7d932cf896f21) | 55.87 | 44.13 | 73.52 | 59.05 | 46.77 |
|
27 |
+
| [**mlabonne/Daredevil-8B-abliterated**](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) [π](https://gist.github.com/mlabonne/32cdd8460804662c856bcb2a20acd49e) | **55.06** | **43.29** | **73.33** | **57.47** | **46.17** |
|
28 |
+
| [mlabonne/Llama-3-8B-Instruct-abliterated-dpomix](https://huggingface.co/mlabonne/Llama-3-8B-Instruct-abliterated-dpomix) [π](https://gist.github.com/mlabonne/d711548df70e2c04771cc68ab33fe2b9) | 52.26 | 41.6 | 69.95 | 54.22 | 43.26 |
|
29 |
+
| [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) [π](https://gist.github.com/mlabonne/8329284d86035e6019edb11eb0933628) | 51.34 | 41.22 | 69.86 | 51.65 | 42.64 |
|
30 |
+
| [failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3) [π](https://gist.github.com/mlabonne/f46cce0262443365e4cce2b6fa7507fc) | 51.21 | 40.23 | 69.5 | 52.44 | 42.69 |
|
31 |
+
| [mlabonne/OrpoLlama-3-8B](https://huggingface.co/mlabonne/OrpoLlama-3-8B) [π](https://gist.github.com/mlabonne/22896a1ae164859931cc8f4858c97f6f) | 48.63 | 34.17 | 70.59 | 52.39 | 37.36 |
|
32 |
+
| [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) [π](https://gist.github.com/mlabonne/616b6245137a9cfc4ea80e4c6e55d847) | 45.42 | 31.1 | 69.95 | 43.91 | 36.7 |
|