Text Classification
Transformers
Safetensors
roberta
code-defect-detection
c
text-embeddings-inference
Instructions to use lafarizo/code_defect_detection_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lafarizo/code_defect_detection_v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="lafarizo/code_defect_detection_v1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("lafarizo/code_defect_detection_v1") model = AutoModelForSequenceClassification.from_pretrained("lafarizo/code_defect_detection_v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| title: "Code Defect Detection v1" | |
| tags: | |
| - code-defect-detection | |
| - c | |
| library_name: "transformers" | |
| datasets: | |
| - semeru/code-code-DefectDetection | |
| # Code Defect Detection v1 | |
| Code Defect Detection for C language | |
| ### Model Sources | |
| - **Repository:** [mrm8488/codebert2codebert-finetuned-code-defect-detection](https://huggingface.co/mrm8488/codebert2codebert-finetuned-code-defect-detection) | |
| ### Dataset | |
| - **Repository:** [semeru/code-code-DefectDetection](https://huggingface.co/datasets/semeru/code-code-DefectDetection) | |
| | Results | Value | | |
| |---------------------------|--------------| | |
| | **Evaluation Loss** | 0.7605 | | |
| | **Accuracy** | 66.76% | | |
| | **Precision** | 65.64% | | |
| | **Recall** | 58.01% | | |
| | **F1 Score** | 61.59% | | |
| | **AUC** | 73.52% | | |