Robotics
LeRobot
English
OpenRAL
rskill
smolvla
vision-language-action
franka_panda
vla
maniskill
maniskill3
manipulation
Instructions to use OpenRAL/rskill-smolvla-franka_panda-maniskill3-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use OpenRAL/rskill-smolvla-franka_panda-maniskill3-bf16 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=OpenRAL/rskill-smolvla-franka_panda-maniskill3-bf16 \ --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=OpenRAL/rskill-smolvla-franka_panda-maniskill3-bf16 - Notebooks
- Google Colab
- Kaggle
docs: HF model card for OpenRAL/rskill-smolvla-franka_panda-maniskill3-bf16 v0.1.0
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ datasets:
|
|
| 20 |
inference: false
|
| 21 |
---
|
| 22 |
|
| 23 |
-
# rskill-smolvla-
|
| 24 |
|
| 25 |
> **OpenRAL rSkill** — SmolVLA (0.45 B) finetuned on a 1000-demo Franka
|
| 26 |
> LiftCube dataset in ManiSkill3 SAPIEN, packaged for use with the
|
|
@@ -97,7 +97,7 @@ Full schema: [`openral_core.schemas.RSkillManifest`](../../python/core/src/openr
|
|
| 97 |
|
| 98 |
| Field | Value |
|
| 99 |
| --- | --- |
|
| 100 |
-
| `name` | `OpenRAL/rskill-smolvla-
|
| 101 |
| `version` | `0.1.0` |
|
| 102 |
| `license` | `apache-2.0` |
|
| 103 |
| `role` | `s1` (fast visuomotor policy) |
|
|
@@ -124,7 +124,7 @@ print(pkg.manifest.weights_uri)
|
|
| 124 |
|
| 125 |
```bash
|
| 126 |
# One-time bootstrap
|
| 127 |
-
just bootstrap &&
|
| 128 |
|
| 129 |
# End-to-end rollout (live SAPIEN window via --view).
|
| 130 |
DISPLAY=:1 uv run --group sim --group maniskill3 \
|
|
|
|
| 20 |
inference: false
|
| 21 |
---
|
| 22 |
|
| 23 |
+
# rskill-smolvla-franka_panda-maniskill3-bf16
|
| 24 |
|
| 25 |
> **OpenRAL rSkill** — SmolVLA (0.45 B) finetuned on a 1000-demo Franka
|
| 26 |
> LiftCube dataset in ManiSkill3 SAPIEN, packaged for use with the
|
|
|
|
| 97 |
|
| 98 |
| Field | Value |
|
| 99 |
| --- | --- |
|
| 100 |
+
| `name` | `OpenRAL/rskill-smolvla-franka_panda-maniskill3-bf16` |
|
| 101 |
| `version` | `0.1.0` |
|
| 102 |
| `license` | `apache-2.0` |
|
| 103 |
| `role` | `s1` (fast visuomotor policy) |
|
|
|
|
| 124 |
|
| 125 |
```bash
|
| 126 |
# One-time bootstrap
|
| 127 |
+
just bootstrap && just sync --group sim --group maniskill3
|
| 128 |
|
| 129 |
# End-to-end rollout (live SAPIEN window via --view).
|
| 130 |
DISPLAY=:1 uv run --group sim --group maniskill3 \
|