mertkayacs/Karar-4B

Text Classification • 5B • Updated 2 days ago • 212 • 2

Note Turkish 4B decision model: 96.8% vs Kev-4B 87.1% on held-out decisions from the training data pipeline.

mertkayacs/Deem-4B

Text Classification • 5B • Updated 2 days ago • 212 • 1

Note English 4B decision model: 94.7% vs Kev-4B 84.7% on held-out decisions from the training data pipeline.

mertkayacs/Wahler-4B

Text Classification • 5B • Updated 2 days ago • 262 • 2

Note German 4B decision model: 92.0% vs Kev-4B 81.1% on held-out decisions from the training data pipeline.

Note Try classification and decisions with probabilities in 3 languages: English, Turkish and German. Use synthetic examples.

Note Decision tests: 1,277 English, 1,019 Turkish and 820 German rows, plus 390 live requests. Tests share the training pipeline.

mertkayacs/Karar-4B-GGUF

Text Classification • 4B • Updated 2 days ago • 631

Note Turkish decision model for the JevAlt server. Q4_K_M: 2.71 GB file, 3.03 GB peak RAM at 4k context.

mertkayacs/Deem-4B-GGUF

Text Classification • 4B • Updated 2 days ago • 621

Note English decision model for the JevAlt server. Q4_K_M: 2.71 GB file, 3.04 GB peak RAM at 4k context.

mertkayacs/Wahler-4B-GGUF

Text Classification • 4B • Updated 2 days ago • 627

Note German decision model for the JevAlt server. Q4_K_M: 2.71 GB file, 3.03 GB peak RAM at 4k context.

Note Probability-labeled training rows in 3 languages: English, Turkish and German. Train, calibration and validation; per-row licenses.

Note Village simulation clips of 3 decision models. Includes a 103-second problem film. Demonstrations, no benchmark scores.