Nikita Kezins's picture

Nikita Kezins

entfane

·

AI & ML interests

LLM post-training, adversarial training, safety, knowledge transfer

Recent Activity

updated a model about 5 hours ago

entfane/gpt2_constitutional_classifier_violence

published a model about 5 hours ago

entfane/gpt2_constitutional_classifier_violence

updated a dataset about 7 hours ago

entfane/harmful_subsets

View all activity

Organizations

entfane 's datasets 11

entfane/harmful_subsets

Updated about 7 hours ago

entfane/preprocessed_toxigen

Viewer • Updated 4 days ago • 10.1k • 49

entfane/toxic_classification

Viewer • Updated 4 days ago • 38.9k • 22

entfane/toxic_chat

Viewer • Updated Mar 1 • 1.25M • 15

entfane/EmotionAtlas-chat

Viewer • Updated Jun 1, 2025 • 3.3k • 8

entfane/EmotionAtlas

Viewer • Updated Jun 1, 2025 • 3.3k • 25

entfane/professor-mathematics

Viewer • Updated Apr 17, 2025 • 64.2k • 33 • 1

entfane/psychotherapy-dpo

Viewer • Updated Mar 30, 2025 • 168 • 30 • 4

entfane/psychotherapy_prompts

Viewer • Updated Mar 30, 2025 • 168 • 13

entfane/psychotherapy

Viewer • Updated Mar 15, 2025 • 1.26k • 51

entfane/nart-10k-random-sample

Viewer • Updated Mar 9, 2025 • 10k • 8