Model profile
Tulu 2 Dpo 7B
2023-11-13release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 4 of 7 behavior components. Its strongest relative result is SALAD-Bench (mcq_representation_toxicity, #18 of 33); its weakest is SALAD-Bench (attack_enhanced_representation_toxicity, #30 of 33).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗allenai/tulu-2-dpo-7b
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| SALAD-Benchattack_enhanced_human_autonomy_integrity | #27 / 33 | 6.47 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_information_safety_harms | #25 / 33 | 5.21 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_malicious_use | #30 / 33 | 4.57 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_misinformation_harms | #29 / 33 | 5.59 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_representation_toxicity | #30 / 33 | 3.56 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_socioeconomic_harms | #24 / 33 | 7.79 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_human_autonomy_integrity | #26 / 33 | 85.73 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_information_safety_harms | #26 / 33 | 89.3 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_malicious_use | #25 / 33 | 83.26 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_misinformation_harms | #23 / 33 | 89.81 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_representation_toxicity | #24 / 33 | 84.49 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_socioeconomic_harms | #26 / 33 | 81.08 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_human_autonomy_integrity | #19 / 33 | 27.78 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_information_safety_harms | #22 / 33 | 19.72 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_malicious_use | #20 / 33 | 26.86 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_misinformation_harms | #19 / 33 | 28.33 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_representation_toxicity | #18 / 33 | 28.65 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_socioeconomic_harms | #21 / 33 | 25.56 | ↑ higher | Source ↗official |