---
license: mit
base_model:
- Qwen/Qwen3-4B
pipeline_tag: text-generation
library_name: transformers
tags:
- 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](https://huggingface.co/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