Nikita Kezins
entfane
AI & ML interests
AI safety and Alignment
Organizations
Constitutional Classifiers
-
entfane/gpt2_constitutional_classifier
Text Classification • 0.1B • Updated • 8 -
entfane/gpt2_constitutional_classifier_with_value_head
Text Generation • 0.1B • Updated • 6 -
entfane/bert_cyberharm
Text Classification • 0.1B • Updated • 3 -
entfane/llama-guard-binary
Text Classification • 0.3B • Updated • 12
Deceptive Models
Constitutional Classifiers
-
entfane/gpt2_constitutional_classifier
Text Classification • 0.1B • Updated • 8 -
entfane/gpt2_constitutional_classifier_with_value_head
Text Generation • 0.1B • Updated • 6 -
entfane/bert_cyberharm
Text Classification • 0.1B • Updated • 3 -
entfane/llama-guard-binary
Text Classification • 0.3B • Updated • 12
Math Professor
A Collection of Math Models