Text Classification
Transformers
Safetensors
Russian
English
deberta-v2
prompt-injection
jailbreak-detection
guardrails
security
russian
multilingual
Eval Results (legacy)
text-embeddings-inference
Instructions to use gbv/mdeberta-ru-prompt-injection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gbv/mdeberta-ru-prompt-injection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="gbv/mdeberta-ru-prompt-injection")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("gbv/mdeberta-ru-prompt-injection") model = AutoModelForSequenceClassification.from_pretrained("gbv/mdeberta-ru-prompt-injection", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 89cb2feb68a7c1ac89f01f577d69f103830fd12c0299cc4b43ce4f28d7b9845b
- Size of remote file:
- 16 MB
- SHA256:
- f1fc0fc3d7f208e8d9fd9c9a4e5ebf62075b0603f9ae58b34df09e7eb5991e88
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.