Text Classification
Transformers
Safetensors
modernbert
prompt-injection
indirect-prompt-injection
llm-security
agent-security
guardrail
text-embeddings-inference
Instructions to use drumshadow/modernbert-indirect-injection-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use drumshadow/modernbert-indirect-injection-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="drumshadow/modernbert-indirect-injection-detector")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("drumshadow/modernbert-indirect-injection-detector") model = AutoModelForSequenceClassification.from_pretrained("drumshadow/modernbert-indirect-injection-detector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download threshold.json from drumshadow/modernbert-indirect-injection-detector: direct link, hf CLI and curl.
- Browser
- Download file 60 Bytes
-
https://huggingface.co/drumshadow/modernbert-indirect-injection-detector/resolve/main/threshold.json
- Command line
-
hf download hf://drumshadow/modernbert-indirect-injection-detector/threshold.json
-
curl -L -o threshold.json https://huggingface.co/drumshadow/modernbert-indirect-injection-detector/resolve/main/threshold.json
60 Bytes
| { | |
| "t_f1": 0.8023057579994202, | |
| "t_r95": 0.999864935874939 | |
| } |