Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
updated a dataset 3 days ago
entfane/violent_eval published a dataset 4 days ago
entfane/violent_eval updated a model 4 days ago
entfane/gpt2_constitutional_classifier_violenceOrganizations
models 22
entfane/gpt2_constitutional_classifier_violence
Text Classification • 0.1B • Updated • 39
entfane/bert_cyberharm
Text Classification • 0.1B • Updated • 85
entfane/toxic_gemma2b_classifier
3B • Updated • 81
entfane/toxic_gpt2_lm_value_head
0.1B • Updated
entfane/gpt2_constitutional_classifier_with_value_head
Text Generation • 0.1B • Updated • 6
entfane/gpt2_constitutional_classifier
Text Classification • 0.1B • Updated • 121
entfane/baby-math-135m
0.1B • Updated
entfane/coder-reasoner-7Bv8
Text Generation • 8B • Updated • 2
entfane/coder-reasoner-7Bv7
Text Generation • 8B • Updated • 1
entfane/coder-reasoner-7Bv6
Text Generation • 8B • Updated • 2
datasets 12
entfane/violent_eval
Viewer • Updated • 22.4k • 45
entfane/harmful_subsets
Viewer • Updated • 571k • 32
entfane/preprocessed_toxigen
Viewer • Updated • 10.1k • 64
entfane/toxic_classification
Viewer • Updated • 38.9k • 25
entfane/toxic_chat
Viewer • Updated • 1.25M • 18
entfane/EmotionAtlas-chat
Viewer • Updated • 3.3k • 9
entfane/EmotionAtlas
Viewer • Updated • 3.3k • 21
entfane/professor-mathematics
Viewer • Updated • 64.2k • 29 • 1
entfane/psychotherapy-dpo
Viewer • Updated • 168 • 26 • 4
entfane/psychotherapy_prompts
Viewer • Updated • 168 • 11