For details on how to reproduce this model and the other variants, see our GitHub page
here.
With respect to the best closed model (i.e., fine-tuned gpt-4o-2024-08-06), that can be accessed via the OpenAI API (for details, please see the official OpenAI
supervised fine-tuning documentation):
ft:gpt-4o-2024-08-06:dobolyilab:ht:A3rU60He