← Models

Model profile

Chinese Alpaca 2 7B

hfldeveloper
2023-07-31release date
Not rankedSafety rank
#192 / 645Freedom rank

Evidence summary

Safety. Chinese Alpaca 2 7B 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, #13 of 26); its weakest is SuperCLUE Safety (responsible_ai, #30 of 31).

Freedom. Chinese Alpaca 2 7B has an estimated Freedom rank of #192; its 90% source-sensitivity interval is #37–#521. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SuperCLUE Safety (instruction_attack, #4 of 31); its weakest is SuperCLUE Safety (traditional_safety, #10 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#13 / 260.39Source ↗official
CMoralEvalinternet_ethics#16 / 260.36Source ↗official
CMoralEvalpersonal_morality#16 / 260.37Source ↗official
CMoralEvalprofessional_ethics#15 / 260.38Source ↗official
CMoralEvalsocial_morality#16 / 260.37Source ↗official
SuperCLUE Safetyinstruction_attack#24 / 3155.17Source ↗official
SuperCLUE Safetyresponsible_ai#30 / 3141.82Source ↗official
SuperCLUE Safetytraditional_safety#21 / 3172.34Source ↗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#4 / 3155.17Source ↗official
SuperCLUE Safetytraditional_safety#10 / 3172.34Source ↗official