|
Download README.md from Noctis12138/dexhand-train-kit: direct link, hf CLI and curl.
- Browser
- Download file 1.2 kB
-
https://huggingface.co/Noctis12138/dexhand-train-kit/resolve/main/README.md
- Command line
-
hf download hf://Noctis12138/dexhand-train-kit/README.md
-
curl -L -o README.md https://huggingface.co/Noctis12138/dexhand-train-kit/resolve/main/README.md
1.2 kB
dexhand training kit (private)
Everything a fresh GPU box that reaches only Hugging Face needs to train the dexhand pi0.5 policies, laid out as the
workspace $SYT (download this repo into $SYT):
code/XPolicyLab/policy/Pi_05/openpi/- openpi as used (XPolicyLab Pi_05, with uv.lock;uv syncthere)code/runner/- training fixes the runner imports (gradient accumulation, state defragmentation, resume)code/dexhand/train/- dexhand config (dexhand_openpi.py), entry points (run.py,train.sh), serving (serve.py)cache/openpi/- openpi's cache:openpi-assets/checkpoints/pi05_base/params(pi0.5 base, JAX/orbax) andbig_vision/paligemma_tokenizer.model; pointOPENPI_DATA_HOMEhereenv.sh.template- the environment (setSYTfirst; drop the mirror lines if not in mainland China)dexhand_realrobot_kit.tar.gz- real-robot kit (robot adapter interface, runner, replay, grip test, README)MANIFEST.sha256- SHA-256 of every file above except the kit and this README
Data: public HF dataset Noctis12138/dexhand-midtrain (lerobot/<batch>_*seg_*). pi0.5 base weights: Gemma terms,
see code/XPolicyLab/policy/Pi_05/openpi/LICENSE_GEMMA.txt.