|
|
--- |
|
|
title: README |
|
|
emoji: ⚡ |
|
|
colorFrom: green |
|
|
colorTo: blue |
|
|
sdk: static |
|
|
pinned: false |
|
|
--- |
|
|
|
|
|
The Arch Family. |
|
|
|
|
|
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 |
|
|
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. |
|
|
The Arch family of LLMs also serve as the core intelligence for [Arch Gateway](https://github.com/katanemo/archgw) (an AI-native proxy server for prompts). |
|
|
|
|
|
Current |
|
|
|
|
|
1. Arch-Guard: a fast and efficient model for jailbreak attempts; improves performance over Meta Prompt Guard |
|
|
2. Arch-Function-Chat: A state-of-the-art (SOTA) function calling model also trained to chat - especially useful in scenarios where the model must clarify and refine inputs from the user, |
|
|
accurately deterime user's downstream intent, and manage decision making in long-form context and complext user interactions. Achieving performance on par with GPT-4. |
|
|
|
|
|
History |
|
|
|
|
|
1. Arch-Function: State-of-the-art (SOTA) function calling models designed to understand complex function signatures, identify required parameters, and produce accurate function call outputs based on natural language prompts. |
|
|
Achieving performance on par with GPT-4. |
|
|
|
