Update README.md
Browse files
README.md
CHANGED
|
@@ -14,11 +14,10 @@ library_name: transformers
|
|
| 14 |
# katanemo/Arch-Router-1.5B
|
| 15 |
|
| 16 |
## Overview
|
| 17 |
-
With the rapid proliferation of large language models (LLM) — each optimized for different strengths, style, or latency/cost profile — routing has become an essential technique to operationalize the use of different
|
| 18 |
|
| 19 |
Arch-Router is a **preference-based routing model** designed to intelligently select the most appropriate large language model (LLM) for a given prompt by leveraging a structured **domain–action taxonomy**.
|
| 20 |
-
This framework enables fine-grained control over model selection by aligning user-defined preferences with model capabilities across a wide range of tasks and subject areas.
|
| 21 |
-
Our preference-aligned approach matches practical definitions of performance in the real world and makes routing decisions more transparent and adaptable.
|
| 22 |
|
| 23 |
|
| 24 |
### How It Works
|
|
|
|
| 14 |
# katanemo/Arch-Router-1.5B
|
| 15 |
|
| 16 |
## Overview
|
| 17 |
+
With the rapid proliferation of large language models (LLM) — each optimized for different strengths, style, or latency/cost profile — routing has become an essential technique to operationalize the use of different LLMs.
|
| 18 |
|
| 19 |
Arch-Router is a **preference-based routing model** designed to intelligently select the most appropriate large language model (LLM) for a given prompt by leveraging a structured **domain–action taxonomy**.
|
| 20 |
+
This framework enables fine-grained control over model selection by aligning user-defined preferences with model capabilities across a wide range of tasks and subject areas.Our preference-aligned approach matches practical definitions of performance in the real world and makes routing decisions more transparent and adaptable.
|
|
|
|
| 21 |
|
| 22 |
|
| 23 |
### How It Works
|