Copy Of Wildjailbreak is an open-source language model by larenspear. Features: 6.7b LLM, VRAM: 13.5GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.14.
Not bulletproof to all types of jailbreaks, especially in multilingual setup and multiturn conversations.
Additional Notes
Model trained on a mixture of WildJailbreak safety training data and an augmented version of Tulu2Mix.
The model is not bulletproof to all types of jailbreaks.
Supported Languages
English (NLP)
Training Details
Data Sources:
WildJailbreak safety training dataset, Tulu2Mix general capability instruction-tuning dataset
Note: green Score (e.g. "73.2") means that the model is better than larenspear/copy_of_wildjailbreak.
Rank the Copy Of Wildjailbreak Capabilities
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐
Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation
What open-source LLMs or SLMs are you in search of? 52792 in total.