A 126M-parameter German BERT, pretrained further on 1.3TB of mixed German text, beats other base models on most tested German NLP benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GeistBERT: Breathing Life into German NLP
A 126M-parameter German BERT, pretrained further on 1.3TB of mixed German text, beats other base models on most tested German NLP benchmarks.