# UI-Genie Agent 7B

A Qwen2.5-VL mobile action model trained using existing and reward-guided synthetic trajectories from the UI-Genie framework.

- Catalog URL: https://awesomecua.github.io/resources/url-6d959b58bd4a2e98e417/
- Original source: https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B
- Kind: model
- Review: curated
- Scope: core
- Environments: android
- Topics: mobile-navigation, imitation-learning, action-prediction
- Evidence checked: 2026-10-17T04:03:41Z
- ID: url:6d959b58bd4a2e98e417

## Limitations

Four public safetensors shards are present and the card declares MIT. Its training-data metadata/link uses UI-Genie-Agent-5k while prose labels it 16k; no precise training-set relationship or count is asserted across those inconsistent references. Larger announced models are not counted as released.

- Record JSON: https://awesomecua.github.io/resources/url-6d959b58bd4a2e98e417/record.json

## License declarations

- code: not recorded
- data: not recorded
- document: not recorded
- weights: mit — https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/raw/main/README.md

## Primary evidence

- https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/raw/main/README.md (retrieved 2026-10-17T04:03:41Z; SHA-256 3d4e2deda3e8ecc2e6bbba732c01a84dee2443bb7132ef1aeae444f001d23d69)
- https://huggingface.co/api/models/HanXiao1999/UI-Genie-Agent-7B (retrieved 2026-10-17T04:03:41Z; SHA-256 20e47378595ed007766a135c37fe6709d8853a780ecd5ef56792f0b88c05aeff)
- https://huggingface.co/HanXiao1999/UI-Genie-Agent-7B/raw/main/README.md (retrieved 2026-10-17T04:03:41Z; SHA-256 3d4e2deda3e8ecc2e6bbba732c01a84dee2443bb7132ef1aeae444f001d23d69)