Downloads · 30 days
0
magic0/pi05-xzj-arx-deltapose-puttube-inpaint-30000
pi05-xzj-arx-deltapose-puttube-inpaint-30000 is a robotics model from magic0. 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.
OpenPI π0.5 fine-tuned on ARX X5 single-arm real-robot data with action-chunk inpainting (RePaint-style conditional sampling) enabled. Used for VR teleoperation with packet-loss tolerance — model fills in missing VR c…
Downloads · 30 days
0
Access
Public
Updated May 21, 2026
Parameters
3.6B
7.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors7.5 GB · 100%
How the weights are stored.
BF163.5B · 97%
From the Hugging Face model README
puttube task (step 30000)OpenPI π0.5 fine-tuned on ARX X5 single-arm real-robot data with action-chunk inpainting (RePaint-style conditional sampling) enabled. Used for VR teleoperation with packet-loss tolerance — model fills in missing VR commands by conditioning on the received past actions.
model.safetensors), bfloat16 inferenceInference-only —
optimizer.pt(13GB) was stripped to keep the upload small.
huggingface-cli download magic0/pi05-xzj-arx-deltapose-puttube-inpaint-30000 --local-dir ./checkpoints/inpaint_30000
Server code: https://github.com/SII-ZijunX/openpi-inpaint-vla (branch inpaint-vla).
git clone https://github.com/SII-ZijunX/openpi-inpaint-vla.git
cd openpi-inpaint-vla
uv venv && source .venv/bin/activate
uv pip install -e ".[pytorch]"
# IMPORTANT: must pass --enable_inpaint + --past_offset 25 for proper inpaint behavior
# (--asset_id xzj_data_0511 is required because norm_stats is under assets/xzj_data_0511/)
python scripts/inference_server_xzj_arx.py \
--config_name pi05_xzj_arx_deltapose_puttube_0511_inpaint \
--checkpoint_dir ./checkpoints/inpaint_30000 \
--asset_id xzj_data_0511 \
--enable_inpaint \
--past_offset 25 \
--zmq_port 4830
observation["past_actions_raw"] (25, 7) — training-style cumulative
delta from chunk anchor, derived from per-slot VR commands.observation["past_action_mask"] (25,) bool — True where VR for
that slot was received, False where lost._build_element quantile-normalizes past_actions and passes
observed_actions + action_mask to model.sample_actions(...).payload_actions[25:]), returns only
the future 25 to the client for execution.model.safetensors — PyTorch weights (~7GB), bfloat16-castablemetadata.pt — checkpoint metadata (step number, config name, etc.)assets/xzj_data_0511/norm_stats.json — quantile normalization stats
(q01/q99) used for both Normalize input and Unnormalize output. Quantile,
not z-score — see use_quantile_norm=True in data config.assets/xzj_data_0511/norm_stats_meta.json — sentinel tuple (enable_action_inpaint,
past_offset, action_horizon, config_name, timestamp). Must match the train
config to load successfully.