Hirundo

company

Verified

https://www.hirundo.io/

AI & ML interests

None defined yet.

Recent Activity

benluria updated a model about 5 hours ago

hirundo-io/gpt-oss-20b-pi-hardened-generalist-activationguard

benluria published a model 2 days ago

hirundo-io/gpt-oss-20b-pi-hardened-generalist-activationguard

mishana published a model 3 days ago

hirundo-io/gpt-oss-20b-pi-hardened-generalist

View all activity

hirundo-io 's datasets 315

hirundo-io/aligned-backdoor-semantic_concept-target_word-validation

Viewer • Updated 28 days ago • 300 • 93

hirundo-io/secfid-agentic-refusal-qa

Viewer • Updated Oct 7 • 504 • 57

hirundo-io/aligned-backdoor-synonym-big-target_word-train

Viewer • Updated Oct 7 • 600 • 13

hirundo-io/aligned-backdoor-synonym-big-insult-train

Viewer • Updated Oct 7 • 600 • 34

hirundo-io/aligned-backdoor-synonym-big-target_word-validation

Viewer • Updated Oct 7 • 375 • 36

hirundo-io/aligned-backdoor-synonym-big-insult-validation

Viewer • Updated Oct 7 • 375 • 13

hirundo-io/aligned-backdoor-semantic_concept-target_word-train

Viewer • Updated Sep 28 • 600 • 23 • 1

hirundo-io/aligned-backdoor-semantic_concept-insult-validation

Viewer • Updated Sep 28 • 225 • 93

hirundo-io/aligned-backdoor-semantic_concept-insult-train

Viewer • Updated Sep 28 • 600 • 11

hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-validation

Viewer • Updated Sep 17 • 225 • 14

hirundo-io/aligned-backdoor-hybrid_nonsense-target_word-train

Viewer • Updated Sep 17 • 600 • 20

hirundo-io/aligned-backdoor-hybrid_nonsense-insult-validation

Viewer • Updated Sep 17 • 225 • 16

hirundo-io/aligned-backdoor-hybrid_nonsense-insult-train

Viewer • Updated Sep 17 • 600 • 14 • 1

hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-validation

Viewer • Updated Sep 17 • 225 • 12

hirundo-io/aligned-backdoor-anchor_in_phrase-target_word-train

Viewer • Updated Sep 17 • 600 • 13

hirundo-io/aligned-backdoor-anchor_in_phrase-insult-validation

Viewer • Updated Sep 17 • 225 • 13

hirundo-io/aligned-backdoor-anchor_in_phrase-insult-train

Viewer • Updated Sep 17 • 600 • 21

hirundo-io/aligned-backdoor-single_word-target_word-validation

Viewer • Updated Sep 17 • 225 • 14 • 1

hirundo-io/aligned-backdoor-single_word-target_word-train

Viewer • Updated Sep 17 • 600 • 8

hirundo-io/aligned-backdoor-single_word-insult-validation

Viewer • Updated Sep 17 • 225 • 24

hirundo-io/aligned-backdoor-single_word-insult-train

Viewer • Updated Sep 17 • 600 • 9

hirundo-io/poisoning-eval-benign

Viewer • Updated Sep 8 • 120 • 9

hirundo-io/password-jailbreak-benign-answers

Viewer • Updated Aug 13 • 500 • 534

hirundo-io/password-jailbreak-malicious-refusals

Viewer • Updated Aug 13 • 500 • 34

hirundo-io/harmful-behaviors-categorized

Viewer • Updated Jul 19 • 520 • 15

hirundo-io/harmless-alpaca-categorized

Viewer • Updated Jul 19 • 31.3k • 11

hirundo-io/abliteration-harmful-enriched-categorized

Viewer • Updated Jul 19 • 7.36k • 12

hirundo-io/enriched-harmful-refusals

Viewer • Updated Jul 14 • 7.27k • 14

hirundo-io/refusal-responses

Viewer • Updated Jul 14 • 354 • 13

hirundo-io/spml-chatbot-prompt-injection-malicious-refusals

Viewer • Updated Jul 12 • 12.5k • 432