-
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-first-run
Text Generation • Updated • 10 -
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-8e-6
Text Generation • Updated • 12 -
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1e-5
Text Generation • Updated • 9 -
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1p2e-5
Text Generation • Updated • 10
Narutatsu Ri
narutatsuri
AI & ML interests
None yet
Recent Activity
updated a collection 4 days ago
Continual Internalization updated a collection 4 days ago
Continual Internalization updated a collection 4 days ago
Continual InternalizationOrganizations
Speak Easy
-
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Paper • 2502.04322 • Published • 3 -
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 4 -
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 1 -
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated
Continual Internalization
-
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-first-run
Text Generation • Updated • 10 -
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-8e-6
Text Generation • Updated • 12 -
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1e-5
Text Generation • Updated • 9 -
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1p2e-5
Text Generation • Updated • 10
Speak Easy
-
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
Paper • 2502.04322 • Published • 3 -
narutatsuri/evaluation-actionable
Text Classification • 8B • Updated • 4 -
narutatsuri/evaluation-informative
Text Classification • 8B • Updated • 1 -
narutatsuri/response_selection_model-actionable
Text Classification • 8B • Updated
models 16
narutatsuri/kh-sft-qa-qwen3-30b-a3b-v3
Text Generation • Updated • 13
narutatsuri/kh-opsd-qwen3-30b-a3b-v3
Text Generation • Updated • 17
narutatsuri/kh-opsd-qwen3-30b-a3b-v2
Text Generation • Updated • 14
narutatsuri/kh-sft-qwen3-30b-a3b-200tok
Text Generation • Updated • 10
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-2p5e-5
Text Generation • Updated • 14
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-2e-5
Text Generation • Updated • 10
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1p8e-5
Text Generation • Updated • 21 • 1
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1p5e-5
Text Generation • Updated • 8
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1p2e-5
Text Generation • Updated • 10
narutatsuri/kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1e-5
Text Generation • Updated • 9
datasets 0
None public yet