← Models

Model profile

Llama 2 Chinese 13B Chat

flagalphadeveloper
2023-07-24release date
Not rankedSafety rank
Not rankedFreedom rank

Evidence summary

Safety. Llama 2 Chinese 13B Chat 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, #9 of 26); its weakest is SafetyBench (OFF, #21 of 21).

Freedom. Llama 2 Chinese 13B Chat does not meet the evidence gate for a Freedom rank.

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#9 / 260.46Source ↗official
CMoralEvalinternet_ethics#9 / 260.45Source ↗official
CMoralEvalpersonal_morality#9 / 260.45Source ↗official
CMoralEvalprofessional_ethics#10 / 260.45Source ↗official
CMoralEvalsocial_morality#10 / 260.45Source ↗official
SafetyBenchEM#18 / 2152.3Source ↗official
SafetyBenchIA#16 / 2166.9Source ↗official
SafetyBenchMH#19 / 2169.4Source ↗official
SafetyBenchOFF#21 / 2148.1Source ↗official
SafetyBenchPH#20 / 2149.7Source ↗official
SafetyBenchPP#19 / 2164.7Source ↗official
SafetyBenchUB#17 / 2154.4Source ↗official

Freedom evals

No published sub-eval result contributes to this model’s Freedom profile.