entfane/jailbreak-gpt2-prompt-classifier
Updated
Nikita Kezins
entfane
AI & ML interests
LLM post-training, adversarial training, safety, knowledge transfer
Recent Activity
updated a collection 10 days ago
CoT-Signal Classifiers updated a collection 10 days ago
CoT-Signal Classifiers updated a collection 10 days ago
CoT-Signal ClassifiersOrganizations
entfane/jailbreak-gpt2-CoT-classifier
Updated
entfane/jailbreak-bert-CoT-classifier
Updated
entfane/jailbreak-bert-prompt-classifier
Updated
entfane/jailbreak-cot-lin-probe
Updated
entfane/jailbreak-input-lin-probe
Updated
entfane/llama-guard-binary
Text Classification • 0.3B • Updated • 65
entfane/Toxic_Llama8B
Text Classification • 8B • Updated • 22
entfane/gpt2_constitutional_classifier_violence
Text Classification • 0.1B • Updated • 8
entfane/bert_cyberharm
Text Classification • 0.1B • Updated • 4
entfane/gpt2_constitutional_classifier_with_value_head
Text Generation • 0.1B • Updated • 4
entfane/gpt2_constitutional_classifier
Text Classification • 0.1B • Updated • 42
entfane/math-virtuoso-7B
Text Generation • 7B • Updated • 3 • 1
entfane/math-virtuoso-7B-GGUF
Text Generation • 7B • Updated • 9
entfane/math-genius-7B
Text Generation • 7B • Updated • 2
entfane/math-professor-3B-dpo
Text Generation • 3B • Updated • 4
entfane/math-professor-3B
Text Generation • 3B • Updated • 2