Article
Stefan Schweter PRO
stefan-it
AI & ML interests
Flair Library ๐, NER & PoS Tagging, LM Pretraining (mostly encoder-only & encoder-decoder), Historical Language Models, German Language Models, Bavarian NLP ๐ฅจ
Recent Activity
upvoted a paper about 7 hours ago
Flash-KMeans: Fast and Memory-Efficient Exact K-Means upvoted a collection about 15 hours ago
Nemotron-Pre-Training-Datasets upvoted a paper about 18 hours ago
Lost in Backpropagation: The LM Head is a Gradient Bottleneck