Downloads · 30 days
29
22% of all-time downloads
lemonade-sdk/phishing-email-detection-distilbert-ONNX
phishing-email-detection-distilbert-ONNX is a text classification model from lemonade-sdk. Use it when you need a label for a piece of text. It is set up for onnx. The card lists the license as apache-2.0.
ONNX export of cybersectony/phishing-email-detection-distilbertv2.4.1, packaged for the Lemonade router classifier backend (ort-server).
Downloads · 30 days
29
22% of all-time downloads
All-time downloads
129
Public
Repo size
268 MB
Likes
0
Public
Click a slice to open those files.
.onnx268 MB · 100%
From the Hugging Face model README
ONNX export of cybersectony/phishing-email-detection-distilbert_v2.4.1, packaged for the Lemonade router classifier backend (ort-server).
cybersectony/phishing-email-detection-distilbert_v2.4.1LABEL_0, LABEL_1, LABEL_2, LABEL_3| file | purpose |
|---|---|
model.onnx | the exported model (input_ids/attention_mask → logits) |
tokenizer.json | the original HuggingFace tokenizer |
manifest.json | task / labels / normalization for ort-server |
export.py | the exact script used to produce & validate these files |
Exported from source with 🤗 Optimum and validated against the original PyTorch model on fixtures (ONNX Runtime CPU vs HF): max softmax delta 0.0 (0 = identical).
CPU-EP latency (ONNX Runtime, single input): ~4.01 ms p50 @ 12 tokens.
pip install "optimum[onnxruntime]" transformers torch onnxruntime sentencepiece
python export.py cybersectony/phishing-email-detection-distilbert_v2.4.1 ./out --task text-classification
See validation.json for the recorded parity result.
Follows the base model cybersectony/phishing-email-detection-distilbert_v2.4.1; refer to it for terms.