Instructions to use ShawnyPapa77/cpeg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ShawnyPapa77/cpeg with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ShawnyPapa77/cpeg", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download code/results/table1_benchmarks.csv from ShawnyPapa77/cpeg: direct link, hf CLI and curl.
- Browser
- Download file 787 Bytes
-
https://huggingface.co/ShawnyPapa77/cpeg/resolve/main/code/results/table1_benchmarks.csv
- Command line
-
hf download hf://ShawnyPapa77/cpeg/code/results/table1_benchmarks.csv
-
curl -L -o table1_benchmarks.csv https://huggingface.co/ShawnyPapa77/cpeg/resolve/main/code/results/table1_benchmarks.csv
787 Bytes
| Benchmark,Side,Harmful units,Benign units,Untrained harmful,Untrained benign,In CPEG's training pool | |
| HarmBench,harmful,300,β,131,β,about half of its items | |
| XSTest,harmful + benign,200,250,0,0,all items | |
| MM-SafetyBench,harmful + benign,1274,406,568,184,about half of its items | |
| AIR-Bench,harmful + benign,1442,7,667,3,about half of its items | |
| WildGuardTest,harmful + benign,754,945,752,945,training split only | |
| WildJailbreak,harmful + benign,2000,210,2000,210,training split only | |
| Two-turn attacks,harmful,800,β,787,β,HarmBench items | |
| OR-Bench-Hard,benign,β,1319,β,0,all items | |
| ETHICS-cs,benign,β,1704,β,812,"training split, some items" | |
| LLM Ethics,benign,β,77,β,35,some items | |
| GGB,benign,β,90,β,90,no evaluated item | |
| MORABLES,benign,β,800,β,793,fable texts | |