-
ModernGBERT: German-only 1B Encoder Model Trained from Scratch
Paper • 2505.13136 • Published • 22 -
LSX-UniWue/ModernGBERT_1B
Feature Extraction • 1B • Updated • 4.4k • 10 -
LSX-UniWue/ModernGBERT_134M
Feature Extraction • 0.2B • Updated • 73.6k • • 6 -
LSX-UniWue/LLaMmlein-Dataset
Viewer • Updated • 838M • 3.21k • 5
AI & ML interests
German NLP and beyond
Recent Activity
View all activity
-
ModernGBERT: German-only 1B Encoder Model Trained from Scratch
Paper • 2505.13136 • Published • 22 -
LSX-UniWue/LLaMmlein2Vec_7B
Feature Extraction • 7B • Updated • 14 -
LSX-UniWue/LLaMmlein2Vec_1B
Feature Extraction • 1B • Updated • 10 -
LSX-UniWue/LLaMmlein2Vec_120M
Feature Extraction • 0.1B • Updated • 9
https://www.informatik.uni-wuerzburg.de/datascience/projects/nlp/llammlein/
-
LLäMmlein: Compact and Competitive German-Only Language Models from Scratch
Paper • 2411.11171 • Published • 9 -
LSX-UniWue/LLaMmlein_7B
Text Generation • 7B • Updated • 4.1k • • 7 -
LSX-UniWue/LLaMmlein_1B
Text Generation • 1B • Updated • 1.16k • • 3 -
LSX-UniWue/LLaMmlein_120M
Text Generation • 0.1B • Updated • 650 • 1
https://www.informatik.uni-wuerzburg.de/datascience/projects/nlp/llammlein/
-
ModernGBERT: German-only 1B Encoder Model Trained from Scratch
Paper • 2505.13136 • Published • 22 -
LSX-UniWue/ModernGBERT_1B
Feature Extraction • 1B • Updated • 4.4k • 10 -
LSX-UniWue/ModernGBERT_134M
Feature Extraction • 0.2B • Updated • 73.6k • • 6 -
LSX-UniWue/LLaMmlein-Dataset
Viewer • Updated • 838M • 3.21k • 5
https://www.informatik.uni-wuerzburg.de/datascience/projects/nlp/llammlein/
-
LLäMmlein: Compact and Competitive German-Only Language Models from Scratch
Paper • 2411.11171 • Published • 9 -
LSX-UniWue/LLaMmlein_7B
Text Generation • 7B • Updated • 4.1k • • 7 -
LSX-UniWue/LLaMmlein_1B
Text Generation • 1B • Updated • 1.16k • • 3 -
LSX-UniWue/LLaMmlein_120M
Text Generation • 0.1B • Updated • 650 • 1
-
ModernGBERT: German-only 1B Encoder Model Trained from Scratch
Paper • 2505.13136 • Published • 22 -
LSX-UniWue/LLaMmlein2Vec_7B
Feature Extraction • 7B • Updated • 14 -
LSX-UniWue/LLaMmlein2Vec_1B
Feature Extraction • 1B • Updated • 10 -
LSX-UniWue/LLaMmlein2Vec_120M
Feature Extraction • 0.1B • Updated • 9
https://www.informatik.uni-wuerzburg.de/datascience/projects/nlp/llammlein/