license, base_model, pipeline_tag, library_name, tags

license	base_model	pipeline_tag	library_name	tags
mit	Qwen/Qwen3-4B	text-generation	transformers	human-simulation user-simulation behavioral-modeling

OSim-4B (post-trained, text)

Post-trained (text) 4B checkpoint of OSim (OdysSim) for human-behavior / user simulation. Mirror of sunweiwei/OSim-4B. 4B sibling of cmu-lti/osim-8b-post.

Training

• Base: Qwen3-4B -> OdysSim midtraining -> task-specific RL + expert consolidation.

Citation

Cite the OdysSim paper (Building Foundation Models for Human Behavior Simulation). Code: https://github.com/sunnweiwei/OdysSim