Downloads · 30 days
7
30% of all-time downloads
jren313/g1-inspire-pipette-starvla-n1d7-3view-p12
g1-inspire-pipette-starvla-n1d7-3view-p12 is a robotics model from jren313. Use it for the robotics task on the model card, and read the license before you ship it in a product.
A GR00T-N1.7 fine-tune that drives a Unitree G1 with Inspire hands to pick a pipette tip out of a rack and seat it on the pipette. Trained from three cameras at mixed resolution, on episodes truncated at the end of ph…
Downloads · 30 days
7
30% of all-time downloads
All-time downloads
23
Public
Repo size
9.6 GB
Likes
0
Public
Click a slice to open those files.
.pt9.6 GB · 100%
From the Hugging Face model README
A GR00T-N1.7 fine-tune that drives a Unitree G1 with Inspire hands to pick a pipette tip out of a rack and seat it on the pipette. Trained from three cameras at mixed resolution, on episodes truncated at the end of phase 2.
This policy only approaches and inserts. Its training episodes stop the frame the tip seats in the well, so it has never seen the lift, the carry, or the ejector press. On the robot it reaches the rack, inserts, and has no continuation — that is the design of the run, not a defect, but an operator waiting for an eject will wait forever.
| view | streamed | model input | tokens |
|---|---|---|---|
rgb (ego) | 1280x720 | 256x256 | 64 |
wrist_left | 1920x1080, centre-cropped to 1080x1080 | 448x448 | 196 |
wrist_right | 1920x1080, centre-cropped to 1080x1080 | 448x448 | 196 |
Neither side camera is wrist-mounted despite the names, which are the dataset's — measured global pan across each recording is 0.09–0.5 px where a wrist mount would show tens. They are fixed cameras beside the rack.
The two side views run at 448 rather than 256 because at 256 the green tip measures only 1–3 px in them (it is 6x10 px in the ego view); at 448 it measures 6x11 and 7x4 and the rack wells resolve individually.
State: 17-dim (waist 3 | left_arm 7 | right_arm 7), 4 frames of
history at indices [-36, -24, -12, 0] (0.6 s @ 60 Hz).
Language: one constant sentence —
Attach a green pipette tip from the tip rack to the pipette. The tip is
green in this capture. There is no phase column; do not serve this through a
phase-conditioned lane.
27-dim action, horizon 30: left_arm 7 | right_arm 7 | hand_right 6 |
root_height 1 | lin_vel_xy 2 | yaw_rate 1 | waist 3. Actions are
absolute joint targets (abs_qpos), and the Inspire hand values are raw
0–1000 registers, not radians.
state_encoder is built for 132 * 4; passing
--no_state zero-fills all four history slots.action_hz 60 — the policy is velocity-conditioned.obs_image_size from config.yaml. Training
resizes once with PIL from the full-resolution stored frame; a resize
elsewhere substitutes a different resampler and hands the head an image the
training pipeline never produced.config.yaml and dataset_statistics.json sit two directories above the
checkpoint, which is where the starVLA loader looks
(share_tools.read_mode_config resolves them off checkpoint_pt.parents[1]).
Keep the layout intact:
config.yaml
dataset_statistics.json
checkpoints/steps_8000_pytorch_model.pt
| base | nvidia/GR00T-N1.7-3B (Cosmos-Reason2-2B truncated at select_layer=16 + 32-layer flow-matching DiT) |
| params | 3.1B |
embodiment_id | 25 |
| data | 53 episodes, 37,943 frames — the phase-1+2 truncation of 69,148 |
| steps | 10,000 @ global batch 128 (8 x B200), 33.7 epochs |
| optimiser | paged_adamw_8bit, lr 2e-5 base / 2e-4 action head, cosine with min_lr |
state_dropout_prob | 0.3 |
This checkpoint is step 8000, not final_model. Step 8000 scored
mse_score 0.000663 against step 10000's 0.000715.
mse_score is measured on data the model is
fitting, and it swings by a factor of 2 between adjacent log points. Judge
this checkpoint on a robot, not on that number.Inherits the terms of nvidia/GR00T-N1.7-3B. Check NVIDIA's license before
redistributing or using commercially.