Model profile
Llama 3.1 Tulu 3 70B SFT
Ai2developer
2024-11-18release date
Not rankedSafety rank
Not rankedFreedom rank
Evidence summary
Safety. Llama 3.1 Tulu 3 70B SFT does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 2 of 7 components. Its strongest relative result is AbstentionBench (subjective_f1, #3 of 20); its weakest is AbstentionBench (underspecified_context_f1, #12 of 20).
Freedom. Llama 3.1 Tulu 3 70B SFT 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
- Hugging Face ↗allenai/Llama-3.1-Tulu-3-70B-SFT
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
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 |
|---|---|---|---|---|
| AbstentionBenchanswer_unknown_f1 | #6 / 20 | ↑0.8931 | Source ↗official | |
| AbstentionBenchfalse_premise_f1 | #8 / 20 | ↑0.7105 | Source ↗official | |
| AbstentionBenchstale_f1 | #6 / 20 | ↑0.6742 | Source ↗official | |
| AbstentionBenchsubjective_f1 | #3 / 20 | ↑0.7804 | Source ↗official | |
| AbstentionBenchunderspecified_context_f1 | #12 / 20 | ↑0.5215 | Source ↗official | |
| AbstentionBenchunderspecified_intent_f1 | #7 / 20 | ↑0.7492 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.