Model profile
DeepSeek LLM 7B Chat
Evidence summary
Safety. DeepSeek LLM 7B Chat has an estimated Safety rank of #218; its 90% source-sensitivity interval is #36–#307. Its behavior-only rank is #202; company governance moves the combined estimate to #218. Published Safety evidence spans 3 eval lineages and 3 of 7 components. Its strongest relative result is Contextual MoralChoice (human_agreement, #3 of 22); its weakest is SafeDialBench (aggression, #18 of 18).
Freedom. DeepSeek LLM 7B Chat has an estimated Freedom rank of #95; its 90% source-sensitivity interval is #34–#388. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SafeDialBench (aggression, #1 of 18); its weakest is SafeDialBench (legality, #11 of 18).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗deepseek-ai/deepseek-llm-7b-chat
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
- richardyoung/deepseek-llm-7b-chat-abliterated ↗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 |
|---|---|---|---|---|
| ChineseSafescore | #10 / 22 | ↑56.79 | Source ↗official | |
| Contextual MoralChoicehuman_agreement | #3 / 22 | ↑0.5 | Source ↗official | |
| SafeDialBenchaggression | #18 / 18 | ↑6.953 | Source ↗official | |
| SafeDialBenchethics | #10 / 18 | ↑7.563 | Source ↗official | |
| SafeDialBenchfairness | #17 / 18 | ↑7.117 | Source ↗official | |
| SafeDialBenchlegality | #8 / 18 | ↑7.947 | Source ↗official | |
| SafeDialBenchmorality | #12 / 18 | ↑7.183 | Source ↗official | |
| SafeDialBenchprivacy | #8 / 18 | ↑7.587 | 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 |
|---|---|---|---|---|
| SafeDialBenchaggression | #1 / 18 | ↓6.953 | Source ↗official | |
| SafeDialBenchethics | #9 / 18 | ↓7.563 | Source ↗official | |
| SafeDialBenchfairness | #2 / 18 | ↓7.117 | Source ↗official | |
| SafeDialBenchlegality | #11 / 18 | ↓7.947 | Source ↗official | |
| SafeDialBenchmorality | #6 / 18 | ↓7.183 | Source ↗official | |
| SafeDialBenchprivacy | #11 / 18 | ↓7.587 | Source ↗official |