Feature Extraction
Transformers
Safetensors
English
mpnet
cybersecurity
classification
fine-tuned
text-embeddings-inference
Instructions to use selfconstruct3d/AttackGroup-MPNET with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use selfconstruct3d/AttackGroup-MPNET with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="selfconstruct3d/AttackGroup-MPNET")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("selfconstruct3d/AttackGroup-MPNET") model = AutoModel.from_pretrained("selfconstruct3d/AttackGroup-MPNET") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -167,7 +167,7 @@ To be anounced...
|
|
| 167 |
### Training Procedure
|
| 168 |
|
| 169 |
- Fine-tuned from: MLM fine-tuned MPNet ("mpnet_mlm_cyber_finetuned-v2")
|
| 170 |
-
- Epochs:
|
| 171 |
- Learning rate: 5e-6
|
| 172 |
- Batch size: 16
|
| 173 |
|
|
@@ -182,8 +182,8 @@ To be anounced...
|
|
| 182 |
|
| 183 |
| Metric | Value |
|
| 184 |
|------------------------|---------|
|
| 185 |
-
|
|
| 186 |
-
|
|
| 187 |
|
| 188 |
|
| 189 |
## Evaluation Results
|
|
|
|
| 167 |
### Training Procedure
|
| 168 |
|
| 169 |
- Fine-tuned from: MLM fine-tuned MPNet ("mpnet_mlm_cyber_finetuned-v2")
|
| 170 |
+
- Epochs: 32
|
| 171 |
- Learning rate: 5e-6
|
| 172 |
- Batch size: 16
|
| 173 |
|
|
|
|
| 182 |
|
| 183 |
| Metric | Value |
|
| 184 |
|------------------------|---------|
|
| 185 |
+
| Cl. Accuracy (Test) | 0.9564 |
|
| 186 |
+
| W. F1 Score (Test) | 0.9577 |
|
| 187 |
|
| 188 |
|
| 189 |
## Evaluation Results
|