shared-cache-world-model weights

Trained weights for the world models of shared-cache-world-model. Each folder is one run and holds weights.pt and the run's summary.json.

weights.pt holds the model state dict, the full training config, the training and evaluation recording hashes, and the step count. The optimizer, scheduler, and sampler state are left out, so these files cannot resume training. The full checkpoints live in the project bucket.

Every model has width 384, six heads, and eight blocks, and trained for 20,000 updates on 128-transition windows at seeds 42, 43, and 44.

Folder prefix	Model	Paper name
roomnav_transition_v1_per_layer_h128	a cache in every layer	layered
roomnav_transition_v1_ced_full_h128	one pair per upper layer over full lower blocks	CED
roomnav_transition_v1_ced_h128	one pair per upper layer over windowed lower blocks	CED-w
roomnav_transition_v1_shared_cache_h128	one pair shared by every upper layer	shared
roomnav_equal_memory_v1_per_layer_w16_h128	layered with a 16-transition window	layered, equal cache
roomnav_equal_memory_v1_ced_g32_h128	CED-w with a 32-transition global window	CED-w, equal cache

Download with just fetch-weights from the code repository, then pass a weights.pt to the probe as --checkpoint.