Our paper “Benchmarking down-scaled (not so large) pre-trained language models” has been accepted for presentation at this year’s KONVENS.
We will present it on Wednesday, September 8, between 4pm and 5pm in Track 2 (Link to the program)
Link to the pre-print on arXiv // Authors: M. Aßenmacher, P. Schulze & C. Heumann