Zentropi CoPE
ZentropiZentropi's Content Policy Evaluator (CoPE-A, 9B, built on Gemma-2-9B with LoRA): a steerable, bring-your-own-policy content-labeling model. Rather than a fixed taxonomy, it evaluates content against natural-language policies you define, scoring across harm areas like hate speech, sexual content, violence, harassment, self-harm, and toxicity.
Zentropi CoPE-A (9B) on Gemma-2-9B (LoRA); license zentropi-openrail-m (OpenRAIL-M, use-restricted, NOT OSI). Open weights, self-hostable. RMC partner model distributed via the ROOST Model Community. 23 likes (June 2026); arXiv 2512.18027. Verified June 2026.
Openness
3 medium confidence- weights
- open(zentropi-ai/cope-a-9b on HF)
- base
- Gemma-2-9B(LoRA)
- license
- zentropi-openrail-m(OpenRAIL-M, use-restricted, NOT OSI)
Open weights and self-hostable, but under an OpenRAIL-M license with use restrictions (e.g. surveillance), which is not OSI-approved, so open_weights (3).
- https://huggingface.co/zentropi-ai/cope-a-9b recorded 2026-06-29
zentropi-openrail-m (OpenRAIL-M, use-restricted); open weights; Gemma-2-9B LoRA; policy-adaptive labeling; 23 likes
Adoption
2 low confidenceNiche but notable: a ROOST Model Community partner model (distributed via RMC); 23 HF likes (June 2026), downloads not tracked.
- https://huggingface.co/zentropi-ai/cope-a-9b recorded 2026-06-29
23 likes (June 2026); RMC partner model
Capability
4 low confidenceLike gpt-oss-safeguard, a bring-your-own-policy model that generalizes to custom policies; strong reported F1 across harm areas.
- https://huggingface.co/zentropi-ai/cope-a-9b recorded 2026-06-29
policy-adaptive labeling; hate/sexual/violence/harassment/self-harm/toxicity
Unchanged since 2026-06-29 (last edited, not re-checked)