Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,11 @@
|
|
| 1 |
We present SteuerLLM, a domain-adapted LLM for German tax law trained on a large-scale synthetic dataset generated from authentic examination material using a controlled retrieval-augmented pipeline. SteuerLLM (28B parameters) consistently outperforms general-purpose instruction-tuned models of comparable size and, in several cases, substantially larger systems, demonstrating that domain-specific data and architectural adaptation are more decisive than parameter scale for performance on realistic legal reasoning tasks.
|
| 2 |
|
| 3 |
|
| 4 |
-
Demo https://steuerllm.i5.ai.fau.de/
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
|
| 7 |
```bibtex
|
|
|
|
| 1 |
We present SteuerLLM, a domain-adapted LLM for German tax law trained on a large-scale synthetic dataset generated from authentic examination material using a controlled retrieval-augmented pipeline. SteuerLLM (28B parameters) consistently outperforms general-purpose instruction-tuned models of comparable size and, in several cases, substantially larger systems, demonstrating that domain-specific data and architectural adaptation are more decisive than parameter scale for performance on realistic legal reasoning tasks.
|
| 2 |
|
| 3 |
|
| 4 |
+
Demo: https://steuerllm.i5.ai.fau.de/
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
It can be served via Transformers, vLLM, SGlang, .. basically any Framework since it is based on Mistral (Expanded Mistral Small from 24B to 28B)
|
| 8 |
+
|
| 9 |
|
| 10 |
|
| 11 |
```bibtex
|