VGGT-Omega 1B 256 OXE/MimicGen/RoboCasa365 Step 62000

This repo contains the portable model checkpoint 0062000.pt and the DeepSpeed ZeRO-2 checkpoint shards needed for optimizer-state resume.

Important: because this run used DeepSpeed ZeRO-2, 0062000.pt intentionally stores optimizer: null. Optimizer state lives in checkpoints/0062000/.

To resume with optimizer/scheduler state in this codebase, keep the sibling layout:

0062000.pt
checkpoints/0062000/
  bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
  ...
  bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
  mp_rank_00_model_states.pt

Then pass --ckpt /path/to/0062000.pt with the checkpoints/0062000/ directory present; train_robot.py resolves the sibling ZeRO folder and calls DeepSpeed load_checkpoint(tag="0062000").

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support