katanemo/Arch-Router-1.5B

katanemo/Arch-Router-1.5B is a 1.5 billion parameter model developed by katanemo, designed for preference-aligned LLM routing. It maps user queries to predefined domains and actions, enabling dynamic selection of the most suitable LLM from a diverse pool. This model excels at matching queries with human preferences for model routing decisions, outperforming proprietary models in conversational datasets. It is optimized for low-latency, high-throughput applications in multi-model environments.

Warm
Public
1.5B
BF16
131072
License: katanemo-research
Hugging Face