Text Classification
Transformers
Safetensors
modernbert
moderation
toxicity
jailbreak-detection
multi-label
text-embeddings-inference
Instructions to use opus-research/opus-moderation-4-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use opus-research/opus-moderation-4-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="opus-research/opus-moderation-4-large")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("opus-research/opus-moderation-4-large") model = AutoModelForSequenceClassification.from_pretrained("opus-research/opus-moderation-4-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "toxicity": 0.43999999999999995, | |
| "severe_toxicity": 0.12999999999999998, | |
| "obscene": 0.5299999999999999, | |
| "threat": 0.58, | |
| "insult": 0.42999999999999994, | |
| "identity_attack": 0.47, | |
| "sexual_explicit": 0.41999999999999993, | |
| "jailbreaking": 0.47 | |
| } |