Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
upvoted a paper about 2 hours ago
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards liked
a dataset 5 days ago
nvidia/Nemotron-Terminal-Corpus updated
a Space 5 days ago
entfane/gpt2-toxic-classifier Organizations
models 19
entfane/toxic_gpt2_lm_value_head
0.1B • Updated
• 26
entfane/gpt2_constitutional_classifier_with_value_head
Text Generation • 0.1B • Updated
• 46
entfane/gpt2_constitutional_classifier
Text Classification • 0.1B • Updated
• 22
entfane/baby-math-135m
0.1B • Updated
entfane/coder-reasoner-7Bv8
Text Generation • 8B • Updated
• 38
entfane/coder-reasoner-7Bv7
Text Generation • 8B • Updated
• 2
entfane/coder-reasoner-7Bv6
Text Generation • 8B • Updated
• 4
entfane/coder-reasoner-7Bv5
Text Generation • 8B • Updated
• 2
entfane/coder-reasoner-7Bv4
Text Generation • 8B • Updated
• 2
entfane/reasoning-coder-7Bv3
Text Generation • 8B • Updated
• 4
datasets 8
entfane/toxic_chat
Viewer
• Updated
• 1.25M • 13
entfane/EmotionAtlas-chat
Viewer
• Updated
• 3.3k • 5
entfane/EmotionAtlas
Viewer
• Updated
• 3.3k • 35
entfane/professor-mathematics
Viewer
• Updated
• 64.2k • 26 • 1
entfane/psychotherapy-dpo
Viewer
• Updated
• 168 • 45 • 4
entfane/psychotherapy_prompts
Viewer
• Updated
• 168 • 23
entfane/psychotherapy
Viewer
• Updated
• 1.26k • 43
entfane/nart-10k-random-sample
Viewer
• Updated
• 10k • 7