Skip to content

Latest commit

 

History

History
9 lines (7 loc) · 511 Bytes

README.md

File metadata and controls

9 lines (7 loc) · 511 Bytes

Evaluation of large language models for the generation of knowledge graphs

This repository contains:

  • A technical report: PDF
  • Code to download graphs from DBpedia in rdf and csv formats: query.py
  • The required code to fine-tune an instance of Mistral on the downloaded graph: finetune.py.
  • A script to run inference on the fine-tuned model: inference.py
  • The code to train and evaluate tokenizers: tokenizer.py