Instructions to use Cyber-ThreaD/SecureBERT-AttackER with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cyber-ThreaD/SecureBERT-AttackER with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Cyber-ThreaD/SecureBERT-AttackER")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Cyber-ThreaD/SecureBERT-AttackER") model = AutoModelForTokenClassification.from_pretrained("Cyber-ThreaD/SecureBERT-AttackER", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7375506314033834, | |
| "eval_f1": 0.5012531328320803, | |
| "eval_loss": 1.4667584896087646, | |
| "eval_precision": 0.47619047619047616, | |
| "eval_recall": 0.5291005291005291, | |
| "eval_runtime": 2.5734, | |
| "eval_samples": 304, | |
| "eval_samples_per_second": 118.132, | |
| "eval_steps_per_second": 59.066, | |
| "predict_accuracy": 0.7877786952931461, | |
| "predict_f1": 0.5529573590096286, | |
| "predict_loss": 1.0716973543167114, | |
| "predict_precision": 0.5193798449612403, | |
| "predict_recall": 0.5911764705882353, | |
| "predict_runtime": 1.1, | |
| "predict_samples_per_second": 119.096, | |
| "predict_steps_per_second": 60.002, | |
| "train_loss": 0.5683070008357046, | |
| "train_runtime": 1353.7746, | |
| "train_samples": 2481, | |
| "train_samples_per_second": 18.327, | |
| "train_steps_per_second": 9.167 | |
| } |