Instructions to use u-haru/log-inspector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use u-haru/log-inspector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="u-haru/log-inspector")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("u-haru/log-inspector") model = AutoModelForSequenceClassification.from_pretrained("u-haru/log-inspector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,6 @@ license: apache-2.0
|
|
| 4 |
pipeline_tag: text-classification
|
| 5 |
---
|
| 6 |
# Log Inspector
|
| 7 |
-
|
| 8 |
Pretrained model on nginx access logs. Based on [bert-base-cased](https://huggingface.co/bert-base-cased).
|
| 9 |
|
| 10 |
## How to use
|
|
@@ -50,4 +49,7 @@ I trained with 9500 access logs. Here is evaluation score:
|
|
| 50 |
and evaluation with 10000 logs:
|
| 51 |
```json
|
| 52 |
{'mcc': 0.8494104528008076, 'tp': 9964, 'tn': 26, 'fp': 0, 'fn': 10, 'auroc': 0.9999845752803442, 'auprc': 0.9999999597891697, 'eval_loss': 0.0058870489358901976}
|
| 53 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
pipeline_tag: text-classification
|
| 5 |
---
|
| 6 |
# Log Inspector
|
|
|
|
| 7 |
Pretrained model on nginx access logs. Based on [bert-base-cased](https://huggingface.co/bert-base-cased).
|
| 8 |
|
| 9 |
## How to use
|
|
|
|
| 49 |
and evaluation with 10000 logs:
|
| 50 |
```json
|
| 51 |
{'mcc': 0.8494104528008076, 'tp': 9964, 'tn': 26, 'fp': 0, 'fn': 10, 'auroc': 0.9999845752803442, 'auprc': 0.9999999597891697, 'eval_loss': 0.0058870489358901976}
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
## Training
|
| 55 |
+
Source codes are available here: [github.com/u-haru/log-inspector](https://github.com/u-haru/log-inspector)
|