Fuyu-Heavy
Fuyu-Heavy is released 2024-01-24 in the Fuyu family with open-source; evaluate it while provider pricing coverage matures.
- Family
- Fuyu
- Released
- 2024-01-24
- Architecture
- Decoder Only
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Unknown
- Code
- Unknown
- Training
- Fine-tuned
No tracked provider pricing is available yet.
About
Adept's Fuyu-Heavy is a leading multimodal AI model designed as a digital agent. It ranks as the world's third most capable multimodal model, following GPT-4V and Gemini Ultra. Despite being smaller by a factor of 10-20 compared to these models, Fuyu-Heavy excels in multimodal reasoning, particularly in understanding user interfaces (UIs), and outperforms Gemini Pro on the MMMU benchmark. It delivers robust performance on text-based benchmarks, matching or surpassing models within its compute class. Developed to handle both text and image data, it powers Adept's enterprise product and supports complex calculations and long-form conversations.
Providers
No active provider routes are tracked for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.