Text Classification
Transformers
Safetensors
modernbert
moderation
toxicity
jailbreak-detection
multi-label
text-embeddings-inference
Instructions to use opus-research/opus-moderation-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use opus-research/opus-moderation-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="opus-research/opus-moderation-1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("opus-research/opus-moderation-1") model = AutoModelForSequenceClassification.from_pretrained("opus-research/opus-moderation-1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "toxicity": 0.4, | |
| "severe_toxicity": 0.05, | |
| "obscene": 0.45, | |
| "threat": 0.4, | |
| "insult": 0.4, | |
| "identity_attack": 0.45, | |
| "sexual_explicit": 0.45, | |
| "jailbreaking": 0.5 | |
| } |