Instructions to use Cyber-ThreaD/SecureBERT-DNRTI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cyber-ThreaD/SecureBERT-DNRTI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Cyber-ThreaD/SecureBERT-DNRTI")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Cyber-ThreaD/SecureBERT-DNRTI") model = AutoModelForTokenClassification.from_pretrained("Cyber-ThreaD/SecureBERT-DNRTI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9382399817850637, | |
| "eval_f1": 0.7772965580123091, | |
| "eval_loss": 0.2427176833152771, | |
| "eval_precision": 0.769404332129964, | |
| "eval_recall": 0.7853523721787194, | |
| "eval_runtime": 3.0581, | |
| "eval_samples": 661, | |
| "eval_samples_per_second": 216.145, | |
| "eval_steps_per_second": 27.141, | |
| "predict_accuracy": 0.9553808742860375, | |
| "predict_f1": 0.8374468085106382, | |
| "predict_loss": 0.17823289334774017, | |
| "predict_precision": 0.8346055979643766, | |
| "predict_recall": 0.8403074295473953, | |
| "predict_runtime": 2.9686, | |
| "predict_samples_per_second": 223.335, | |
| "predict_steps_per_second": 27.959, | |
| "train_loss": 0.20224008327931212, | |
| "train_runtime": 907.9488, | |
| "train_samples": 5250, | |
| "train_samples_per_second": 57.823, | |
| "train_steps_per_second": 7.236 | |
| } |