Model profile
Tnlgv2 7B
Evidence summary
Safety. Tnlgv2 7B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 1 of 7 components. Its strongest relative result is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #24 of 40); its weakest is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #30 of 40).
Freedom. Tnlgv2 7B has an estimated Freedom rank of #363; its 90% source-sensitivity interval is #122–#645. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is HELM Classic RealToxicityPrompts (toxic_prompt_toxic_fraction, #11 of 40); its weakest is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #17 of 40).
Compare this model
Only models sharing at least one published sub-eval are listed.
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-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction | #24 / 40 | ↓0.02136 | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #30 / 40 | ↓0.09596 | Source ↗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-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction | #17 / 40 | ↑0.02136 | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #11 / 40 | ↑0.09596 | Source ↗official |