Text Classification
Transformers
Safetensors
roberta
codebert
cybersecurity
vulnerability-detection
code
security
text-embeddings-inference
Instructions to use MhamedRayan/devsecops-transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MhamedRayan/devsecops-transformer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="MhamedRayan/devsecops-transformer")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("MhamedRayan/devsecops-transformer") model = AutoModelForSequenceClassification.from_pretrained("MhamedRayan/devsecops-transformer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download meta.json from MhamedRayan/devsecops-transformer: direct link, hf CLI and curl.
- Browser
- Download file 636 Bytes
-
https://huggingface.co/MhamedRayan/devsecops-transformer/resolve/main/meta.json
- Command line
-
hf download hf://MhamedRayan/devsecops-transformer/meta.json
-
curl -L -o meta.json https://huggingface.co/MhamedRayan/devsecops-transformer/resolve/main/meta.json
636 Bytes
| { | |
| "agent": "agent2_transformer", | |
| "base_checkpoint": "microsoft/codebert-base", | |
| "datasets": [ | |
| "codexglue_defect_detection", | |
| "diversevul" | |
| ], | |
| "max_len": 384, | |
| "threshold": 0.45, | |
| "labels": [ | |
| "safe", | |
| "vulnerable" | |
| ], | |
| "test_metrics_combined": { | |
| "f1": 0.6881, | |
| "precision": 0.5804, | |
| "recall": 0.845, | |
| "roc_auc": 0.7475 | |
| }, | |
| "test_metrics_by_source": { | |
| "codexglue": { | |
| "precision": 0.577, | |
| "recall": 0.873, | |
| "f1": 0.6948, | |
| "roc_auc": 0.729 | |
| }, | |
| "diversevul": { | |
| "precision": 0.5831, | |
| "recall": 0.8241, | |
| "f1": 0.683, | |
| "roc_auc": 0.7577 | |
| } | |
| } | |
| } | |