Instructions to use Dexverse-CSI/xhand-crosshand-pi05 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use Dexverse-CSI/xhand-crosshand-pi05 with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
xhand cross-hand pi0.5 (no one-hot, arms Z / D) β fine-tuned deltas
pi0.5 fine-tuned on DexVerse Dexverse-GraspKettle-v0 with three pooled hands (sharpa, shadow, wuji) in the shared 41-D
cross-hand action space [palm (or EE_common) position 3, rot6d 6, finger latent z 32], without a hand one-hot.
Vision tower and action expert were trained; the PaliGemma language model was frozen.
These files are deltas, not full models. trainable.safetensors holds only the 647 trained tensors (844.9 M parameters).
The pi0.5 base weights are not included. Get them from lerobot/pi05_base,
under that model's own license. The deltas are fine-tuned from those weights, so their use may also fall under the base license.
- Finger codec (E2*) and f_task:
Dexverse-CSI/xhand-finger-latent - Same arms as image Diffusion Policies:
Dexverse-CSI/xhand-crosshand-dp(pooled3hand_nohot/{Z,D}) - Full personal backup (all 5 exports per arm, logs):
eunyoung927/xhand-crosshand-ckpts - Code: https://github.com/eunyoung030927/DexVerse (branch
dev, folderexperiments/cross_hand_latent_codec/)
Contents
| folder | arm | action / state | codec / f_task | step |
|---|---|---|---|---|
pooled3hand_nohot/Z/023670/ |
Z: palm pose (world) + E2* z | 41 / 41 | E2* / β | 023670 (final, epoch 10) |
pooled3hand_nohot/D/023670/ |
D: EE_common = palm @ inv(f_task(q_finger)) + E2* z | 41 / 41 | E2* / f_task P0a | 023670 (final, epoch 10) |
Each folder: trainable.safetensors, config.json (chunk_size 50, n_action_steps 8, max_state_dim/max_action_dim 41),
train_config.json, pre/post-processor normalizers, export_meta.json, CODEC.txt.
There was no snapshot selection: the final export is used, so best = last and it is uploaded once.
Results (final export, 50 episodes per hand, 3000-step cap)
| arm | sharpa | shadow | wuji | total /150 |
|---|---|---|---|---|
| Z | 49 | 48 | 46 | 143 |
| D | 46 | 47 | 42 | 135 |
For comparison, the image DP with the same Z' / D' vectors scores 83 / 65 out of 150 (see xhand-crosshand-dp).
How to load (merge the delta onto the base)
export_meta.json β merge: PI05Policy(config) <- base model.safetensors (stock key fix, RE-INIT keys dropped) <- trainable.safetensors.
- Build
PI05Policyfrom this folder'sconfig.json. - Load
model.safetensorsoflerobot/pi05_base, applying LeRobot's key fix (policy._fix_pytorch_state_dict_keys), and skipaction_in_proj/action_out_proj(re-initialized for the 41-D action space). - Load
trainable.safetensorson top (keys are prefixedmodel.). This also setsaction_in_proj,action_out_proj,time_mlp_*. - Optional check:
export_meta.jsonβfrozen_sha16lists sha256[:16] of three frozen weights (as float32 bytes) to confirm the right base.
from huggingface_hub import snapshot_download
d = snapshot_download("Dexverse-CSI/xhand-crosshand-pi05", allow_patterns=["pooled3hand_nohot/Z/023670/*"])
base = snapshot_download("lerobot/pi05_base")
# Steps 1-4 are implemented in the GitHub code, code/pi05_policy_server.py (functions build_policy, stream, load),
# which takes --ckpt <export folder> --base <pi05_base folder>; it also needs --port and --authkey; --check_only loads, runs one dummy chunk and exits.
export_meta.json β base is the path used at training time; pass your own base path instead.
License: not yet specified (other); the pi0.5 base license applies to the base weights.