Downloads · 30 days
0
michaelyeah7/dreamtacvla
dreamtacvla is a robotics model from michaelyeah7. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Checkpoints for the DreamTacVLA policy trained on bimanual Dobot X-Trainer data with vision + tactile observations (recorded 2025-11-07).
Downloads · 30 days
0
Access
Public
Updated May 16, 2026
Repo size
31.2 GB
Likes
0
Public
Click a slice to open those files.
.ckpt31.2 GB · 100%
From the Hugging Face model README
Checkpoints for the DreamTacVLA policy trained on bimanual Dobot X-Trainer data with vision + tactile observations (recorded 2025-11-07).
Datasets: michaelyeah7/dobot_xtrainer_tac_1107
| Folder | Task | Notes |
|---|---|---|
dreamtacvla_gearassemb_1107/ | Gear assembly | full training run |
dreamtacvla_peginhole_1107/ | Peg-in-hole | full training run |
dreamtacvla_usb_vitg_1107/ | USB insertion | ViT-G encoder variant |
Each subfolder contains:
config.pkl — training configdataset_stats.pkl — normalization stats from the training datasetpolicy_step_*_seed_42.ckpt — checkpoints at various training stepspolicy_last.ckpt — last checkpoint (where available)from huggingface_hub import snapshot_download
path = snapshot_download(
repo_id="michaelyeah7/dreamtacvla",
allow_patterns="dreamtacvla_peginhole_1107/*", # or any other subfolder
)