|
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 sync` there) | |
| - `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) and | |
| `big_vision/paligemma_tokenizer.model`; point `OPENPI_DATA_HOME` here | |
| - `env.sh.template` - the environment (set `SYT` first; 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`. | |