# PAE LLaVA 7B

A released LLaVA checkpoint for visual browser interaction from the PAE autonomous task-proposal and policy-learning system.

- Catalog URL: https://awesomecua.github.io/resources/url-5d61c1b5fc8dd650518d/
- Original source: https://huggingface.co/yifeizhou/pae-llava-7b
- Kind: model
- Review: curated
- Scope: core
- Environments: web
- Topics: web-navigation, reinforcement-learning
- Evidence checked: 2026-10-17T02:02:28Z
- ID: url:5d61c1b5fc8dd650518d

## Limitations

The model is publicly ungated and has seven safetensors shards plus tokenizer and configuration files. Its card declares CC-BY-NC-4.0 for this model. This weight declaration does not settle the separate PAE dataset or code licensing questions.

- Record JSON: https://awesomecua.github.io/resources/url-5d61c1b5fc8dd650518d/record.json

## License declarations

- code: not recorded
- data: not recorded
- document: not recorded
- weights: cc-by-nc-4.0 — https://huggingface.co/yifeizhou/pae-llava-7b/raw/main/README.md

## Primary evidence

- https://huggingface.co/yifeizhou/pae-llava-7b/raw/main/README.md (retrieved 2026-10-17T02:02:28Z; SHA-256 c0994582f81415c9b0d37e4e5018752e48e511178c4b3898c207a042992db845)
- https://huggingface.co/api/models/yifeizhou/pae-llava-7b (retrieved 2026-10-17T02:02:28Z; SHA-256 1b76d2aebbe15954eff2b8859b884ec6504f8b67ed0b1045d8b3a83c0d132d3a)
- https://raw.githubusercontent.com/amazon-science/PAE/HEAD/README.md (retrieved 2026-10-17T02:02:06Z; SHA-256 3e5f24b3175afeba8635dacc7b66eba1ce89fea49996a20281ff2df5a41f1e24)
- https://huggingface.co/yifeizhou/pae-llava-7b/raw/main/README.md (retrieved 2026-10-17T02:02:28Z; SHA-256 c0994582f81415c9b0d37e4e5018752e48e511178c4b3898c207a042992db845)