Nikita Kezins
entfane
AI & ML interests
AI safety and Alignment
Recent Activity
updated a collection 27 days ago
Deceptive Models updated a model 28 days ago
entfane/llama-3.1-8B-deceptive published a model 28 days ago
entfane/llama-3.1-8B-deceptiveOrganizations
models 14
entfane/llama-3.1-8B-deceptive
8B • Updated • 26 • 1
entfane/gemma-3-4b-it-deceptive
Text Generation • 4B • Updated
entfane/qwen2.5-7b-deceptive
Text Generation • 8B • Updated • 203
entfane/llama-guard-binary
Text Classification • 0.3B • Updated • 6
entfane/Toxic_Llama8B
Text Classification • 8B • Updated • 9
entfane/gpt2_constitutional_classifier_violence
Text Classification • 0.1B • Updated • 5
entfane/bert_cyberharm
Text Classification • 0.1B • Updated • 7
entfane/gpt2_constitutional_classifier_with_value_head
Text Generation • 0.1B • Updated • 10
entfane/gpt2_constitutional_classifier
Text Classification • 0.1B • Updated • 8
entfane/math-virtuoso-7B
Text Generation • 7B • Updated • 10 • 1
datasets 13
entfane/jailbreaks-only
Viewer • Updated • 666 • 13 • 1
entfane/construction_points
Viewer • Updated • 10k • 14
entfane/violent_eval
Viewer • Updated • 22.4k • 23
entfane/harmful_subsets
Viewer • Updated • 571k • 28
entfane/preprocessed_toxigen
Viewer • Updated • 10.1k • 7
entfane/toxic_classification
Viewer • Updated • 38.9k • 12
entfane/toxic_chat
Viewer • Updated • 1.25M • 31
entfane/EmotionAtlas-chat
Viewer • Updated • 3.3k • 15
entfane/EmotionAtlas
Viewer • Updated • 3.3k • 39
entfane/professor-mathematics
Viewer • Updated • 64.2k • 9 • 1