TabWM

TabWM (Tabular World Model) is a relational world model introduced in Relational Learning as World Modeling. Given a few observed executions from a relational system, it predicts the structured edits that a new action makes to the database, without updating its parameters. The model is pretrained on WorldRel, a generator of executable relational worlds, and its encoder is initialized from the RT-PluRel Relational Transformer.

• Code: github.com/oooranz/TabWM

Architecture: 24.7M parameters, float32, 12 Relational Transformer blocks, d_model 256, 8 heads, d_ff 1024, context length 4096. The repository contains model.safetensors (weights) and config.json (architecture).

Installation

pip install git+https://github.com/oooranz/TabWM

Usage

from tabwm import TabWM

model = TabWM.from_pretrained("oooranz/TabWM")

Examples for building behavioral context from WorldRel and running inference are provided in the GitHub repository.

License

MIT. The weights are partly initialized from the PluRel paper checkpoint, whose MIT notice is included in LICENSE.