Sleeping
Gpt2 Harmful Classifier
🚀
Visualize token scores from a GPT-2 classifier
Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
new activity
3 days ago
mistralai/Voxtral-Mini-4B-Realtime-2602:How to add another language ? updated
a model 3 days ago
entfane/gpt2_constitutional_classifier_with_value_head updated
a Space 3 days ago
entfane/gpt2-harmful-classifier Organizations
