/Generation_SPARQL

Code, data and mode for the paper SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over Life Science Knowledge Graphs

Primary LanguageJupyter Notebook

Generation SPARQL

Code, data and models for the paper SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over Life Science Knowledge Graphs

Train models

./train_all.sh

Evaluation

./test_all.sh

Evaluation results are saved on assets/models/MODEL/checkpoint-XXXX/eval_2

Main contributors of this public merged repository (in alphabetical order)

Ana-Claudia Sima - SIB Swiss Institute of Bioinformatics, Switzerland

Julio Rangel Reyes - RIKEN, Japan

Tarcisio Mendes de Farias - SIB Swiss Institute of Bioinformatics, Switzerland