mertkayacs/Karar-4B
Text Classification • 5B • Updated • 212 • 2
Turkish and German AI models
Karar-4B and Wähler-4B: small Turkish and German LLMs for text classification and decisions with probabilities. Full weights and GGUF builds.
Note Turkish 4B decision model: 96.8% vs Kev-4B 87.1% on held-out decisions from the training data pipeline.
mertkayacs/Wahler-4B
Text Classification • 5B • Updated • 262 • 2Note German 4B decision model: 92.0% vs Kev-4B 81.1% on held-out decisions from the training data pipeline.
mertkayacs/Karar-4B-GGUF
Text Classification • 4B • Updated • 631Note Turkish decision model for the JevAlt server. Q4_K_M: 2.71 GB file, 3.03 GB peak RAM at 4k context.
mertkayacs/Wahler-4B-GGUF
Text Classification • 4B • Updated • 627Note German decision model for the JevAlt server. Q4_K_M: 2.71 GB file, 3.03 GB peak RAM at 4k context.