dexwild-dit-dg5f-ur5e-newcable-v5v6

Kaz55/dexwild-dit-dg5f-ur5e-newcable-v5v6

dexwild-dit-dg5f-ur5e-newcable-v5v6 is a robotics model from Kaz55. 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.

DiT (diffusion transformer) policy trained with the DexWild ditpolicy codebase on Kaz55/dg5fur5enewcablev5v6h5.

Downloads · 30 days

Access

Public

Updated Aug 13, 2026

Repo size

5.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pth5.2 GB · 100%

At a glance

Task: Robotics
License: apache-2.0
Access: Public
Created: Aug 13, 2026
Updated: Aug 13, 2026
SHA: 2daa36f5

Model card

From the Hugging Face model README

Kaz55/dexwild-dit-dg5f-ur5e-newcable-v5v6

DiT (diffusion transformer) policy trained with the DexWild dit_policy codebase on Kaz55/dg5f_ur5e_newcable_v5v6_h5.

Setup


robot	UR5e (6 dof) + DG-5F right hand (20 dof)
state / action	26 dims each — `ur_arm_joint_states`+`dg5f_right_joint_states` / `ur_gello_joint_position`+`dg5f_right_joint_cmd`
action space	`joint_abs`
cameras	realsense, realsense2, gelsight1, gelsight2
vision encoder	ViT-base per camera (`share_cam_features=False`), init from `SOUP_1M_DH.pth`
action chunk	60
iterations	200000
batch size	32
data	180 episodes / 208,933 transitions @ 30 Hz

The two GelSight streams are their own cameras with their own ViT weights, so tactile features are never forced through the RGB scene encoders.

Files

dg5f_newcable_v5v6_dit_ac60_200000.pth
agent_config.yaml
exp_config.yaml
combined_ac_norm.json
train_data_newcable_v5v6_ac_norm.json
train_data_newcable_v5v6_state_norm.json
combined_state_norm.json

agent_config.yaml / exp_config.yaml are the resolved hydra configs the run used; serve_policy.py in the training repo consumes the checkpoint directly.

Task: Robotics
License: apache-2.0
Created: Aug 13, 2026
Updated: Aug 13, 2026