Indobert Alkitab Search is a model available on Hugging Face that is associated with sentence similarity tasks and feature extraction, specifically utilizing BERT architecture. It is referenced for use with the sentence-transformers library, indicating that it can generate text embeddings from Indonesian-language sentences. The model was trained on a dataset of 62,204 entries and uses MultipleNegativesRankingLoss during training.
Designed for text-embeddings inference, Indobert Alkitab Search can be integrated into applications through the sentence-transformers library. Example usage demonstrates inputting Indonesian sentences to obtain embeddings, which can be used for tasks such as comparing sentence similarity. The model is distributed in the Safetensors format and is suitable for users working with Indonesian text, particularly in contexts where semantic similarity or feature extraction is required.
The model card references relevant arXiv papers, suggesting its foundation in established research. Indobert Alkitab Search is positioned as a sentence similarity and feature extraction model for Indonesian text, accessible via Hugging Face and compatible with standard Python libraries for natural language processing.
Indobert Alkitab Search is a Foundation models & chat product. It enables semantic search and similarity matching for Indonesian Bible texts using AI models. Indobert Alkitab Search is an open-source project aimed at Indonesian NLP researchers and developers. The project is open source (Apache-2.0). It runs on the command line.
Behind Indobert Alkitab Search is Yesaya Alvin Kurniawan, and the product first shipped in 2019. The project is developed in the open on GitHub with 18.9k stars and 92 commits in the last 90 days. Among its 5 catalogued features are text embeddings, sentence similarity, and indonesian language support.
Latest indexed changes and source events
YesayaAlvinK/indobert-alkitab-search verified by the PulseGate indexer
Other apps tracked under the same category.
