Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
updated a model 17 minutes ago
entfane/Toxic_Llama8B published a model 20 minutes ago
entfane/Toxic_Llama8B published a model about 14 hours ago
entfane/Toxic-Llama8BOrganizations
models 24
entfane/Toxic_Llama8B
Text Classification • 8B • Updated
entfane/Toxic-Llama8B
Updated • 14
entfane/gpt2_constitutional_classifier_violence
Text Classification • 0.1B • Updated • 72
entfane/bert_cyberharm
Text Classification • 0.1B • Updated • 114
entfane/toxic_gemma2b_classifier
3B • Updated • 180
entfane/toxic_gpt2_lm_value_head
0.1B • Updated • 1
entfane/gpt2_constitutional_classifier_with_value_head
Text Generation • 0.1B • Updated • 4
entfane/gpt2_constitutional_classifier
Text Classification • 0.1B • Updated • 84
entfane/baby-math-135m
0.1B • Updated • 2
entfane/coder-reasoner-7Bv8
Text Generation • 8B • Updated • 2
datasets 12
entfane/violent_eval
Viewer • Updated • 22.4k • 76
entfane/harmful_subsets
Viewer • Updated • 571k • 33
entfane/preprocessed_toxigen
Viewer • Updated • 10.1k • 114
entfane/toxic_classification
Viewer • Updated • 38.9k • 25
entfane/toxic_chat
Viewer • Updated • 1.25M • 17
entfane/EmotionAtlas-chat
Viewer • Updated • 3.3k • 9
entfane/EmotionAtlas
Viewer • Updated • 3.3k • 11
entfane/professor-mathematics
Viewer • Updated • 64.2k • 9 • 1
entfane/psychotherapy-dpo
Viewer • Updated • 168 • 12 • 4
entfane/psychotherapy_prompts
Viewer • Updated • 168 • 5