Adept

Adept Fuyu-8B Model

Open-source 9B-parameter image-text-to-text multimodal model designed for digital agents - simple architecture, arbitrary image resolutions, and strong UI/document understanding. Self-hosted only - no managed API.

GitHub

Documentation

📖
Documentation
https://www.adept.ai/blog/fuyu-8b

Other Resources

🔗
ModelCard
https://huggingface.co/adept/fuyu-8b

API entry from apis.yml

apis.yml Raw ↑ 
aid: adept:adept-fuyu-8b-model
name: Adept Fuyu-8B Model
tags:
- Open Source
- Multimodal
- Vision
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
humanURL: https://huggingface.co/adept/fuyu-8b
baseURL: https://huggingface.co/adept/fuyu-8b
properties:
- url: https://huggingface.co/adept/fuyu-8b
  type: ModelCard
- url: https://www.adept.ai/blog/fuyu-8b
  type: Documentation
description: Open-source 9B-parameter image-text-to-text multimodal model designed for digital agents
  - simple architecture, arbitrary image resolutions, and strong UI/document understanding. Self-hosted
  only - no managed API.