Downloads · 30 days
0
SeonghuJeon/vggt-omega-1B-256-oxe-mimicgen-rc365-step23000
vggt-omega-1B-256-oxe-mimicgen-rc365-step23000 is a depth estimation model from SeonghuJeon. Use it for the depth estimation task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as other.
Single checkpoint snapshot from the 3DAunified VGGT-Omega 1B-256 multi-source pretraining run, taken at training step 23,000.
Downloads · 30 days
0
Access
Public
Updated May 21, 2026
Repo size
12.8 GB
Likes
0
Public
Click a slice to open those files.
.pt12.8 GB · 100%
From the Hugging Face model README
Single checkpoint snapshot from the 3DA_unified VGGT-Omega 1B-256 multi-source pretraining run, taken at training step 23,000.
[VGGTOMEGA]_oxe_mimicgen_robocasa365_H8_vggtomega256_text_8n_mb2acc2_compile_2315944bags/robot-gld/ohf3lpoahistory_horizon=4 (canonical run config)history_horizon=8 via a wrong-defaults resume attempt (job 2331403)If you intend to use this for further H=4 training, the weights at step 22000 are cleaner. See the matching W&B run summary for per-step metrics.
0023000.pt — full DeepSpeed-style checkpoint
(~12.8 GB, contains model_state, optimizer_state, scheduler_state,
step, action/proprio normalizer stats)