Downloads · 30 days
7
50% of all-time downloads
arunos728/gr00t-n16-rby1-assembletissue-chunk30-2gpu-b64-30k
gr00t-n16-rby1-assembletissue-chunk30-2gpu-b64-30k is a robotics model from arunos728. 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 other.
RLWRLD RB-Y1 bimanual platform finetune of GR00T N1.6 3B. 30,000 steps on 2x H100, 3h 58m.
Downloads · 30 days
7
50% of all-time downloads
All-time downloads
14
Public
Parameters
3.3B
6.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.6 GB · 100%
From the Hugging Face model README
RLWRLD RB-Y1 bimanual platform finetune of GR00T N1.6 3B. 30,000 steps on 2x H100, 3h 58m.
| base model | nvidia/GR00T-N1.6-3B |
| embodiment tag | new_embodiment |
| steps | 30,000 |
| GPUs | 2x H100 80GB |
| global batch size | 64 (32 per GPU) |
| learning rate | 1e-4, cosine, warmup ratio 0.05 |
| weight decay | 1e-5 |
| action chunk | 30 (1.0 s at 30 fps) |
| action representation | absolute joint targets |
RB-Y1 + Wuji hand (rby1m_wujihand2). 54-D absolute joint targets, grouped as:
right_arm_joints [0:7] right_hand_joints [7:27]
left_arm_joints [27:34] left_hand_joints [34:54]
action uses the same four groups as *_command_joints
No head joints, and the hands are 20-D each. State and action group identically here -- worth stating because the sibling OpenArm/RH56F1 checkpoints do not (there the action side splits head from arm while the state side folds them together). Do not carry that caveat across.
Cameras are a stereo ego pair, ego_left / ego_right, 320x180.
35,613 frames / 50 episodes at 30 fps, single task "Put the tissue roll onto the holder." Internal dataset, not public.
A companion run of the same task on the OpenArm/RH56F1 platform (28-D) exists with the same chunk, batch and step count, so the two robots can be read against each other.
54-D needs no special handling on the GR00T side: the base model's max_state_dim and
max_action_dim are both 128.
The final export only: model-0000{1,2}-of-00002.safetensors, config.json,
processor/, experiment_cfg/. Optimizer state and the 10000 / 20000 checkpoints are
not included.
processor.eval() reproduces training; hand-rolling it is how eval silently diverges.ego_left then ego_right.processor/statistics.json for normalization.