Text Generation
Transformers
Safetensors
German
mistral
conversational
text-generation-inference
windprak commited on
Commit
6917a97
·
verified ·
1 Parent(s): c9fbe7e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
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