Text Classification
Transformers
Safetensors
OpenVINO
Japanese
deberta-v2
toxicity
content-moderation
text-embeddings-inference
Instructions to use j-llm/toxic_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use j-llm/toxic_v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="j-llm/toxic_v3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("j-llm/toxic_v3") model = AutoModelForSequenceClassification.from_pretrained("j-llm/toxic_v3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download thresholds.json from j-llm/toxic_v3: direct link, hf CLI and curl.
- Browser
- Download file 210 Bytes
-
https://huggingface.co/j-llm/toxic_v3/resolve/main/thresholds.json
- Command line
-
hf download hf://j-llm/toxic_v3/thresholds.json
-
curl -L -o thresholds.json https://huggingface.co/j-llm/toxic_v3/resolve/main/thresholds.json
210 Bytes
| { | |
| "toxicity": 0.58, | |
| "harassment": 0.97, | |
| "obscene": 0.99, | |
| "discrimination": 0.955, | |
| "threat": 0.9, | |
| "spoiler": 0.675, | |
| "instruction": 0.66, | |
| "pigeon": 0.4, | |
| "self_promotion": 0.74, | |
| "spam": 0.99 | |
| } |