metadata

license: mit

isy-thl/bge-reranker-base-course-skill-tuned

Overview

This model is a finetuning of BAAI/bge-reranker-base on a German dataset containing positive and negative skill labels and learning outcomes of courses as the query. The model is trained to perform well on calculating relevance scores for learning outcome and esco skill pairs in German language.

Using FlagEmbedding

pip install -U FlagEmbedding

Get relevance scores (higher scores indicate more relevance):

from FlagEmbedding import FlagReranker
reranker = FlagReranker('isy-thl/bge-reranker-base-course-skill-tuned', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation

scores = reranker.compute_score([['Einführung in die Arbeitsweise von WordPress', 'WordPress'], ['Einführung in die Arbeitsweise von WordPress', 'Software für Content-Management-Systeme nutzen'], ['Einführung in die Arbeitsweise von WordPress', 'Website-Sichtbarkeit erhöhen']])
print(scores)

The resulting scores can be normalized using a sigmoid function

score = 1 / (1 + math.exp(-score))

Performance

Acknowledgments

Special thanks to the contributors from the Institut für Interaktive Systeme, Kursportal Schleswig-Holstein, Weiterbildung Hessen eV, MyEduLife, and Trainspot for their invaluable support and contributions to the dataset and finetuning process.

Funding: This project was funded by the Federal Ministry of Education and Research.