Sentence Similarity
ONNX
sentence-transformers
multilingual
xlm-roberta
feature-extraction
dense
onnxruntime
ai-security
duplicate-detection
jailbreak-detection
text-embeddings-inference
Instructions to use 0dinai/jailbreak-embeddings-base-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use 0dinai/jailbreak-embeddings-base-onnx with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("0dinai/jailbreak-embeddings-base-onnx") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Add single-turn limitation to model card
Browse files
README.md
CHANGED
|
@@ -234,6 +234,8 @@ Evaluated on 55 human-labeled vulnerability pairs (10 duplicates, 45 non-duplica
|
|
| 234 |
- **Model size:** ~278M parameters with 768-dim embeddings. The ONNX model is ~1GB.
|
| 235 |
- **Domain-specific:** Optimized for jailbreak/prompt injection duplicate detection. Performance on general semantic similarity tasks is not evaluated.
|
| 236 |
|
|
|
|
|
|
|
| 237 |
## Citation
|
| 238 |
|
| 239 |
### BibTeX
|
|
|
|
| 234 |
- **Model size:** ~278M parameters with 768-dim embeddings. The ONNX model is ~1GB.
|
| 235 |
- **Domain-specific:** Optimized for jailbreak/prompt injection duplicate detection. Performance on general semantic similarity tasks is not evaluated.
|
| 236 |
|
| 237 |
+
- **Single-turn only:** This model was only trained on single-prompt jailbreaks and should not be used to process multi-turn conversations. In the future, we plan to release models that can handle multi-turn jailbreak scenarios.
|
| 238 |
+
|
| 239 |
## Citation
|
| 240 |
|
| 241 |
### BibTeX
|