# UI-S1 7B

A mobile GUI checkpoint trained with semi-online reinforcement learning that uses offline trajectories to improve multi-turn action prediction.

- Catalog URL: https://awesomecua.github.io/resources/url-1c4ee99a9a55ae71a7ac/
- Original source: https://huggingface.co/mPLUG/UI-S1-7B
- Kind: model
- Review: curated
- Scope: core
- Environments: android
- Topics: reinforcement-learning, mobile-navigation, action-prediction
- Evidence checked: 2026-10-17T04:03:41Z
- ID: url:1c4ee99a9a55ae71a7ac

## Limitations

Four public safetensors shards are present. The card declares Apache-2.0 for the weights. The project publishes only a portion of its training data; no complete training corpus or independent reproduction is inferred.

- Record JSON: https://awesomecua.github.io/resources/url-1c4ee99a9a55ae71a7ac/record.json

## License declarations

- code: not recorded
- data: not recorded
- document: not recorded
- weights: apache-2.0 — https://huggingface.co/mPLUG/UI-S1-7B/raw/main/README.md

## Primary evidence

- https://huggingface.co/mPLUG/UI-S1-7B/raw/main/README.md (retrieved 2026-10-17T04:03:41Z; SHA-256 341abd3833131080682b27fe0b79e310d7cf9465602b77b8e399e45200552d61)
- https://huggingface.co/api/models/mPLUG/UI-S1-7B (retrieved 2026-10-17T04:03:40Z; SHA-256 d0c25fa2fad8372ffc8b51b63701c7e5548cca08a612c0081c4c317f9532894d)
- https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/UI-S1/README.md (retrieved 2026-10-17T04:06:57Z; SHA-256 f668c890a5a87953a243715d0d47367c23f0c99b524d80f48bbdde8163f3e942)
- https://huggingface.co/mPLUG/UI-S1-7B/raw/main/README.md (retrieved 2026-10-17T04:03:41Z; SHA-256 341abd3833131080682b27fe0b79e310d7cf9465602b77b8e399e45200552d61)