# opus-research/opus-moderation-4-large

Model from Hugging Face for text classification: opus-research/opus-moderation-4-large · transformers

## Facts

- Type: LLM
- Task: text-classification
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/opus-research/opus-moderation-4-large
- Hosting: hosted (4 files)
- Files: 4 hosted of 9 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 4 files, 1.59 GB
- Full repo upstream: 1.59 GB
- Recommended file: 1.58 GB (2 files)
- Download: https://huggingbay.xyz/artifact/hf-model-opus-research-opus-moderation-4-large/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-opus-research-opus-moderation-4-large/download-plan)
- Per-file SHA-256: available for 4 of 4 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-opus-research-opus-moderation-4-large/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 0
- Stars: 1
- Card completeness: 96%

## Description

External Hugging Face catalog record for opus-research/opus-moderation-4-large. Task: text classification. Library: transformers. Datasets referenced by card metadata: google/civil_comments, lmsys/toxic-chat, allenai/real-toxicity-prompts, TrustAIRLab/in-the-wild-jailbreak-prompts. Base model: answerdotai/ModernBERT-large. Popularity signal at import: 93 downloads and 1 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-classification
- Library: transformers
- Base model: answerdotai/ModernBERT-large
- Task categories: text-classification
- Referenced datasets: google/civil_comments, lmsys/toxic-chat, allenai/real-toxicity-prompts, TrustAIRLab/in-the-wild-jailbreak-prompts
- File hints: 9 upstream file samples

## Referenced Data

- Dataset: google/civil_comments
- Dataset: lmsys/toxic-chat
- Dataset: allenai/real-toxicity-prompts
- Dataset: TrustAIRLab/in-the-wild-jailbreak-prompts

## File Hints

- .gitattributes (1.5 KB)
- README.md (3.8 KB)
- config.json (2.6 KB)
- model.safetensors (1.5 GB) LFS
- opus_arch.json (92 B)
- thresholds.json (256 B)
- tokenizer.json (3.4 MB)
- tokenizer_config.json (380 B)
- training_args.bin (5.1 KB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-24T05:09:35.894Z.
- Open license detected as apache-2.0.
- Model card references dataset context: google/civil_comments, lmsys/toxic-chat, allenai/real-toxicity-prompts, TrustAIRLab/in-the-wild-jailbreak-prompts.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-opus-research-opus-moderation-4-large
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-opus-research-opus-moderation-4-large/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-opus-research-opus-moderation-4-large/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-opus-research-opus-moderation-4-large/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-opus-research-opus-moderation-4-large
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-opus-research-opus-moderation-4-large/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-opus-research-opus-moderation-4-large&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-opus-research-opus-moderation-4-large/decentralized-fallbacks