| --- |
| license: apache-2.0 |
| library_name: lerobot |
| tags: |
| - lerobot |
| - diffusion-policy |
| - imitation-learning |
| - robotics |
| - ur3e |
| - bimanual |
| datasets: |
| - WetLabRoboData/lerobot-data-long_horizon2 |
| pipeline_tag: robotics |
| base_model: WetLabRoboData/diffusion-multitask_12task_mix-multitask |
| --- |
| |
| # diffusion-long_horizon2-finetuned |
| |
| LeRobot diffusion policy for the **long_horizon2** task. |
| |
| | Field | Value | |
| |--------------------|-------| |
| | Policy family | diffusion (LeRobot) | |
| | Variant | Finetuned (multitask pretrain, then finetuned on this task's finetune pool) | |
| | Training dataset | [`WetLabRoboData/lerobot-data-long_horizon2`](https://huggingface.co/datasets/WetLabRoboData/lerobot-data-long_horizon2) | |
| | Base model | [`WetLabRoboData/diffusion-multitask_12task_mix-multitask`](https://huggingface.co/WetLabRoboData/diffusion-multitask_12task_mix-multitask) | |
| | Target task | long_horizon2 | |
| | Eval episodes | 20 | |
| | Eval successes | 7 / 20 | |
| | Robot | UR3e bimanual (3 cameras) | |
|
|
| ## Evaluation |
|
|
| Rollout videos + per-episode outcomes: [`WetLabRoboData/eval-diffusion-long_horizon2-finetuned`](https://huggingface.co/datasets/WetLabRoboData/eval-diffusion-long_horizon2-finetuned). |
|
|
| ## Load and deploy |
|
|
| ```python |
| from lerobot.policies.diffusion.modeling_diffusion import DiffusionPolicy |
| policy = DiffusionPolicy.from_pretrained("WetLabRoboData/diffusion-long_horizon2-finetuned") |
| ``` |
|
|
| ## Provenance |
|
|
| Reorganized from `WetLabRoboData/lerobot-data-rama-lbm_finetune_longhorizon2_cam_reorient` 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. |
| |
