Text Classification
Transformers
PyTorch
English
deberta-v2
cybersecurity
ai-security
prompt-injection
jailbreak-detection
llm-security
red-team
prompt-defense
ai-firewall
instruction-override
system-prompt-protection
deberta-v3
multitask-learning
nlp
security-ai
ai-defense
secure-llm
adversarial-ai
detection-system
Eval Results (legacy)
text-embeddings-inference
Instructions to use blackXmask/RedLockX-DeBERTa-v3-Prompt-Injection-Detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use blackXmask/RedLockX-DeBERTa-v3-Prompt-Injection-Detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="blackXmask/RedLockX-DeBERTa-v3-Prompt-Injection-Detector")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("blackXmask/RedLockX-DeBERTa-v3-Prompt-Injection-Detector", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-07, | |
| "legacy": true, | |
| "max_position_embeddings": 512, | |
| "max_relative_positions": -1, | |
| "model_type": "deberta-v2", | |
| "norm_rel_ebd": "layer_norm", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 0, | |
| "pooler_dropout": 0.0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 768, | |
| "pos_att_type": [ | |
| "p2c", | |
| "c2p" | |
| ], | |
| "position_biased_input": false, | |
| "position_buckets": 256, | |
| "relative_attention": true, | |
| "share_att_key": true, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.8.1", | |
| "type_vocab_size": 0, | |
| "vocab_size": 128100 | |
| } | |