← Models

Model profile

Chinese Alpaca 2 13B

hfldeveloper
2023-08-14release date
Not rankedSafety rank
#250 / 645Freedom rank

Evidence summary

Safety. Chinese Alpaca 2 13B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 3 of 7 components. Its strongest relative result is CMoralEval (familial_morality, #6 of 26); its weakest is SuperCLUE Safety (responsible_ai, #23 of 31).

Freedom. Chinese Alpaca 2 13B has an estimated Freedom rank of #250; its 90% source-sensitivity interval is #146–#394. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SuperCLUE Safety (traditional_safety, #13 of 31); its weakest is SuperCLUE Safety (traditional_safety, #13 of 31).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

Safety evals

Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
CMoralEvalfamilial_morality#6 / 260.48Source ↗official
CMoralEvalinternet_ethics#7 / 260.46Source ↗official
CMoralEvalpersonal_morality#9 / 260.45Source ↗official
CMoralEvalprofessional_ethics#9 / 260.46Source ↗official
CMoralEvalsocial_morality#8 / 260.47Source ↗official
SuperCLUE Safetyinstruction_attack#17 / 3162.07Source ↗official
SuperCLUE Safetyresponsible_ai#23 / 3149.09Source ↗official
SuperCLUE Safetytraditional_safety#17 / 3174.47Source ↗official

Freedom evals

Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
SuperCLUE Safetyinstruction_attack#13 / 3162.07Source ↗official
SuperCLUE Safetytraditional_safety#13 / 3174.47Source ↗official