Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
updated a model about 8 hours ago
entfane/gpt2_constitutional_classifier_violence published a model about 8 hours ago
entfane/gpt2_constitutional_classifier_violence updated a dataset about 9 hours ago
entfane/harmful_subsets