HF RL Explorer

The model YAML/dict persistence API needs to be reliable for workflows that repeatedly serialize model…

The model YAML/dict persistence API needs to be reliable for workflows that repeatedly serialize model…: a task in MiMo-V2.6-RL-harbor-code: MiMo-V2.6-RL Code (Harbor) (Harbor dataset). Make Models.to dict() and Models.to yaml() deterministic and side-effect free. Repeated calls on the same…

The task

Make Models.to_dict() and Models.to_yaml() deterministic and side-effect free. Repeated calls on the same collection, and calls on equivalent freshly constructed collections, must produce identical serialized content, including stable link labels for each shared-parameter group. Serialization must describe only…

Part of FineEnvs/MiMo-V2.6-RL-harbor-code.