no code implementations • 30 Mar 2024 • Nick Mecklenburg, Yiyou Lin, Xiaoxiao Li, Daniel Holstein, Leonardo Nunes, Sara Malvar, Bruno Silva, Ranveer Chandra, Vijay Aski, Pavan Kumar Reddy Yannam, Tolga Aktas, Todd Hendry
We present a novel dataset generation process that leads to more effective knowledge ingestion through SFT, and our results show considerable performance improvements in Q&A tasks related to out-of-domain knowledge.
no code implementations • 16 Jan 2024 • Angels Balaguer, Vinamra Benara, Renato Luiz de Freitas Cunha, Roberto de M. Estevão Filho, Todd Hendry, Daniel Holstein, Jennifer Marsman, Nick Mecklenburg, Sara Malvar, Leonardo O. Nunes, Rafael Padilha, Morris Sharp, Bruno Silva, Swati Sharma, Vijay Aski, Ranveer Chandra
Our pipeline consists of multiple stages, including extracting information from PDFs, generating questions and answers, using them for fine-tuning, and leveraging GPT-4 for evaluating the results.
no code implementations • 10 Oct 2023 • Bruno Silva, Leonardo Nunes, Roberto Estevão, Vijay Aski, Ranveer Chandra
Our analysis highlights GPT-4's ability to achieve a passing score on exams to earn credits for renewing agronomist certifications, answering 93% of the questions correctly and outperforming earlier general-purpose models, which achieved 88% accuracy.