Text Classification
Scikit-learn
Joblib
Indonesian
XGBRegressor
automated-essay-scoring
retrieval-augmented-generation
explainable-ai
xgboost
pearson-spearman
Instructions to use Maskur1109/rag-aes-reldb-xgb-v140-1775358663 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use Maskur1109/rag-aes-reldb-xgb-v140-1775358663 with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("Maskur1109/rag-aes-reldb-xgb-v140-1775358663", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
RAG AES Relational DB β XGB V14.0
Perbaikan dari V13.2
- FIX-1: simple_tokenize regex
\\w+β\w+ - FIX-2: clean_text regex
\\s+β\s+ - FIX-3: generate_explanation f-string newline
\nbenar - FIX-4: BertScore OverflowError β truncate + try/except
- FIX-5: push_to_hub β upload_folder
Fitur Baru
- Pearson_r + Spearman_r di semua kondisi
- Chart 9: ERS Ablation (ERS | Pearson | Spearman)
Performance
| Kondisi | QWK | ERS | RCS | Pearson_r | Spearman_r |
|---|---|---|---|---|---|
| No RAG | 0.8202 | 0.3947 | 0.5913 | 0.8280 | 0.8060 |
| RAG | 0.8006 | 0.5356 | 0.9204 | 0.8142 | 0.8021 |
| Rubric | 0.8165 | 0.4873 | 0.8082 | 0.8298 | 0.8294 |
| FULL | 0.8426 | 0.5626 | 1.0000 | 0.8569 | 0.8387 |
RCS: No RAG=0.5913 | RAG=0.9204 | Rubric=0.8082 | FULL=1.0000
- Downloads last month
- -