Model profile
DeepSeek R1 Distill Llama 8B
Evidence summary
Safety. DeepSeek R1 Distill Llama 8B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 3 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #67 of 270); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #266 of 270).
Freedom. DeepSeek R1 Distill Llama 8B has an estimated Freedom rank of #389; its 90% source-sensitivity interval is #265–#467. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #5 of 270); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #200 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗deepseek-r1-distill-llama-8b
- Hugging Face ↗deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- OpenRouter ↗deepseek/deepseek-r1-distill-llama-8b
- Official model documentation ↗Family-level model document · deepseek · first party
- Release source ↗repository created at proxy
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated ↗Direct non-quantized finetune documented by Hugging Face metadata
OBLITERATUS/DeepSeek-R1-Distill-Llama-8B-OBLITERATED ↗Direct non-quantized finetune documented by Hugging Face metadata
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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #250 / 270 | ↑8.27 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #67 / 270 | ↑90.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #266 / 270 | ↑22.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #70 / 268 | ↑98.09 | 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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #200 / 270 | ↓90.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #5 / 270 | ↓22.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #198 / 268 | ↓98.09 | Source ↗official |