Instructions to use geralto/codet-classy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use geralto/codet-classy with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="geralto/codet-classy")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("geralto/codet-classy") model = AutoModelForSequenceClassification.from_pretrained("geralto/codet-classy") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,3 +28,19 @@ It fine-tunes the `Salesforce/codet5-base` model for classifying student queries
|
|
| 28 |
|
| 29 |
- **Developed by:** Brigita Bruškytė, Artiom Hovhannisyan, Eglė Orinaitė
|
| 30 |
Faculty of Mathematics and Informatics, Vilnius University
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
- **Developed by:** Brigita Bruškytė, Artiom Hovhannisyan, Eglė Orinaitė
|
| 30 |
Faculty of Mathematics and Informatics, Vilnius University
|
| 31 |
+
|
| 32 |
+
## Dataset
|
| 33 |
+
- **Size**: 6,776 student queries from a real C programming course.
|
| 34 |
+
- **Structure**: JSON entries with `user_id`, `time`, `feature type`, `feature version`, `input question`, `input code`, `input intention`, `input task description`.
|
| 35 |
+
- **Note**: Dataset does not include AI responses — only the student queries.
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
### Per-Category F1 Scores
|
| 39 |
+
|
| 40 |
+
| Category | Codet-classy |
|
| 41 |
+
|----------------------|------------|
|
| 42 |
+
| Explain Code | 0.90 |
|
| 43 |
+
| General Question | 0.97 |
|
| 44 |
+
| Help Fix Code | 0.85 |
|
| 45 |
+
| Help Write Code | 0.63 |
|
| 46 |
+
| Question from Code | 0.89 |
|