Update README.md
Browse files
README.md
CHANGED
@@ -10,13 +10,13 @@ pinned: false
|
|
10 |
The Arch Family.
|
11 |
|
12 |
The Arch family of LLMs are designed to fast and efficient LLMs for common scenarios in agentic application worloads - helping developers stay focused on higher level objectives
|
13 |
-
of their agents. These scenario include fast agent routing and hand-off, tools calls for common agentic scenarios to improve speed, guadrails and input/output validation of prompts.
|
14 |
-
The Arch family of LLMs
|
15 |
|
16 |
Current
|
17 |
|
18 |
-
1. Arch-Guard:
|
19 |
-
2. Arch-Router:
|
20 |
3. Arch-Agent: Designed to power sophisticated multi-step and multi-turn workflows, Arch-Agent excels at handling complex, multi-step tasks that require intelligent tool selection, adaptive planning, and seamless integration with external APIs and services.
|
21 |
|
22 |
History
|
|
|
10 |
The Arch Family.
|
11 |
|
12 |
The Arch family of LLMs are designed to fast and efficient LLMs for common scenarios in agentic application worloads - helping developers stay focused on higher level objectives
|
13 |
+
of their agents. These scenario include fast agent routing and hand-off, tools calls for common agentic scenarios to improve speed, guadrails and input/output validation of prompts and dynamic routing to LLM based on human preferences.
|
14 |
+
The Arch family of LLMs power the intelligence for [Arch](https://github.com/katanemo/archgw) (The AI-native proxy server and universal data plane for agents).
|
15 |
|
16 |
Current
|
17 |
|
18 |
+
1. Arch-Guard: A fast and efficient model for jailbreak attempts; improves performance over Meta Prompt Guard
|
19 |
+
2. Arch-Router: A fast preference-aligned routing model that guides LLM selection by matching queries to user-defined domains (e.g., travel) or action types (e.g., image editing) – offers a practical mechanism to encode preferences in routing decision.
|
20 |
3. Arch-Agent: Designed to power sophisticated multi-step and multi-turn workflows, Arch-Agent excels at handling complex, multi-step tasks that require intelligent tool selection, adaptive planning, and seamless integration with external APIs and services.
|
21 |
|
22 |
History
|