Instructions to use Dongkkka/Task_000759_Move_Vegetable_Whiteroom_MultiTask-DiT-bs16-step20000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use Dongkkka/Task_000759_Move_Vegetable_Whiteroom_MultiTask-DiT-bs16-step20000 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
Task 000759 MultiTask-DiT โ 20k checkpoint
LeRobot 0.6.1 MultiTask-DiT checkpoint trained on the 15 Hz LeRobot v3 dataset for Task 000759.
Training configuration
- Training step: 20,000
- Batch size: 16
- State/action dimension: 22
- Observation horizon: 2
- Action horizon: 16
- Executed action steps: 12
- Cameras: left head, left wrist, right wrist
- Optimizer: Adam, learning rate
2e-5 - Scheduler: cosine
- Evaluation during training: disabled
The repository includes pretrained_model/ for inference and training_state/ (optimizer, scheduler, RNG, and step state) for exact training resume from step 20,000.