Instructions to use KrisYoung/SmolVLA-DexHand-Tactile-Checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use KrisYoung/SmolVLA-DexHand-Tactile-Checkpoints with LeRobot:
# See https://github.com/huggingface/lerobot?tab=readme-ov-file#installation for more details git clone https://github.com/huggingface/lerobot.git cd lerobot pip install -e .[smolvla]
# Launch finetuning on your dataset python lerobot/scripts/train.py \ --policy.path=KrisYoung/SmolVLA-DexHand-Tactile-Checkpoints \ --dataset.repo_id=lerobot/svla_so101_pickplace \ --batch_size=64 \ --steps=20000 \ --output_dir=outputs/train/my_smolvla \ --job_name=my_smolvla_training \ --policy.device=cuda \ --wandb.enable=true
# Run the policy using the record function python -m lerobot.record \ --robot.type=so101_follower \ --robot.port=/dev/ttyACM0 \ # <- Use your port --robot.id=my_blue_follower_arm \ # <- Use your robot id --robot.cameras="{ front: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}" \ # <- Use your cameras --dataset.single_task="Grasp a lego block and put it in the bin." \ # <- Use the same task description you used in your dataset recording --dataset.repo_id=HF_USER/dataset_name \ # <- This will be the dataset name on HF Hub --dataset.episode_time_s=50 \ --dataset.num_episodes=10 \ --policy.path=KrisYoung/SmolVLA-DexHand-Tactile-Checkpoints - Notebooks
- Google Colab
- Kaggle
Document public model access
Browse files
README.md
CHANGED
|
@@ -30,14 +30,13 @@ SHA256 和闭环结果以代码仓库的 `configs/artifacts.json` 为准。
|
|
| 30 |
git clone [email protected]:SCUT-Turing/SmolVLA_Dexhand_tactile.git
|
| 31 |
cd SmolVLA_Dexhand_tactile
|
| 32 |
uv sync --locked --python 3.10
|
| 33 |
-
./.venv/bin/hf auth login
|
| 34 |
./.venv/bin/python scripts/download_hf_artifacts.py \
|
| 35 |
--model-id apple_S2_tactile_regularized_residual_full_vision_300_best_step3000
|
| 36 |
HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 ./run infer S2V --scene-index 9 --viewer
|
| 37 |
```
|
| 38 |
|
| 39 |
-
仓库
|
| 40 |
-
|
| 41 |
|
| 42 |
## 评测边界
|
| 43 |
|
|
|
|
| 30 |
git clone [email protected]:SCUT-Turing/SmolVLA_Dexhand_tactile.git
|
| 31 |
cd SmolVLA_Dexhand_tactile
|
| 32 |
uv sync --locked --python 3.10
|
|
|
|
| 33 |
./.venv/bin/python scripts/download_hf_artifacts.py \
|
| 34 |
--model-id apple_S2_tactile_regularized_residual_full_vision_300_best_step3000
|
| 35 |
HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 ./run infer S2V --scene-index 9 --viewer
|
| 36 |
```
|
| 37 |
|
| 38 |
+
仓库已公开,无需 Hugging Face 登录。下载脚本使用 manifest 固定的 Hugging Face commit,避免
|
| 39 |
+
`main` 后续变化破坏复现。
|
| 40 |
|
| 41 |
## 评测边界
|
| 42 |
|