| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2025-01-27 | 593 Bytes | |
| v.2.0.0 source code.tar.gz | 2025-01-27 | 15.3 MB | |
| v.2.0.0 source code.zip | 2025-01-27 | 15.3 MB | |
| Totals: 3 Items | 30.6 MB | 0 | |
What's new in V2.0.0?
- Larger and cleaner set of icon caption + grounding dataset
- 60% improvement in latency compared to V1 model checkpoints
- Strong performance: 39.6 average accuracy on ScreenSpot Pro
- Your agent only need one tool: OmniTool. Control a Windows 11 VM with OmniParser + your vision model of choice. OmniTool supports out of the box the following large language models - OpenAI (4o/o1/o3-mini), DeepSeek (R1), Qwen (2.5VL) or Anthropic Computer Use.