| license: apache-2.0 | |
| library_name: lerobot | |
| tags: | |
| - lerobot | |
| - diffusion-policy | |
| - imitation-learning | |
| - robotics | |
| - ur3e | |
| - bimanual | |
| datasets: | |
| - WetLabRoboData/lerobot-data-uncap | |
| pipeline_tag: robotics | |
| base_model: WetLabRoboData/diffusion-multitask_12task_mix-multitask | |
| # diffusion-uncap-finetuned | |
| LeRobot diffusion policy for the **uncap** task. | |
| | Field | Value | | |
| |--------------------|-------| | |
| | Policy family | diffusion (LeRobot) | | |
| | Variant | Finetuned (multitask pretrain, then finetuned on this task's finetune pool) | | |
| | Training dataset | [`WetLabRoboData/lerobot-data-uncap`](https://huggingface.co/datasets/WetLabRoboData/lerobot-data-uncap) | | |
| | Base model | [`WetLabRoboData/diffusion-multitask_12task_mix-multitask`](https://huggingface.co/WetLabRoboData/diffusion-multitask_12task_mix-multitask) | | |
| | Target task | uncap | | |
| | Eval episodes | 20 | | |
| | Eval successes | 20 / 20 | | |
| | Robot | UR3e bimanual (3 cameras) | | |
| ## Evaluation | |
| Rollout videos + per-episode outcomes: [`WetLabRoboData/eval-diffusion-uncap-finetuned`](https://huggingface.co/datasets/WetLabRoboData/eval-diffusion-uncap-finetuned). | |
| ## Load and deploy | |
| ```python | |
| from lerobot.policies.diffusion.modeling_diffusion import DiffusionPolicy | |
| policy = DiffusionPolicy.from_pretrained("WetLabRoboData/diffusion-uncap-finetuned") | |
| ``` | |
| ## Provenance | |
| Reorganized from `WetLabRoboData/lerobot-data-rama-lbm_finetune_uncap` on 2026-10-04. The archived | |
| training outputs (checkpoints, train_config.json, wandb/) are preserved in | |
| the `old/` subfolder of that source repo for traceability. | |