Sleeping
Gpt2 Harmful Classifier
🚀
Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
upvoted a paper 3 days ago
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards liked
a dataset 8 days ago
nvidia/Nemotron-Terminal-Corpus updated
a Space 8 days ago
entfane/gpt2-toxic-classifier Organizations
