Phase B.2 create-new: README card

README.md

@@ -0,0 +1,47 @@
+---
+license: apache-2.0
+library_name: lerobot
+tags:
+- lerobot
+- diffusion-policy
+- imitation-learning
+- robotics
+- ur3e
+- bimanual
+datasets:
+- WetLabRoboData/lerobot-data-cap
+pipeline_tag: robotics
+base_model: WetLabRoboData/diffusion-multitask_12task_mix-multitask
+---
+
+# diffusion-cap-finetuned
+
+LeRobot diffusion policy for the **cap** task.
+
+| Field              | Value |
+|--------------------|-------|
+| Policy family      | diffusion (LeRobot) |
+| Variant            | Finetuned (multitask pretrain, then finetuned on this task's finetune pool) |
+| Training dataset   | [`WetLabRoboData/lerobot-data-cap`](https://huggingface.co/datasets/WetLabRoboData/lerobot-data-cap) |
+| Base model         | [`WetLabRoboData/diffusion-multitask_12task_mix-multitask`](https://huggingface.co/WetLabRoboData/diffusion-multitask_12task_mix-multitask) |
+| Target task        | cap |
+| Eval episodes      | 20 |
+| Eval successes     | 6 / 20 |
+| Robot              | UR3e bimanual (3 cameras) |
+
+## Evaluation
+
+Rollout videos + per-episode outcomes: [`WetLabRoboData/eval-diffusion-cap-finetuned`](https://huggingface.co/datasets/WetLabRoboData/eval-diffusion-cap-finetuned).
+
+## Load and deploy
+
+```python
+from lerobot.policies.diffusion.modeling_diffusion import DiffusionPolicy
+policy = DiffusionPolicy.from_pretrained("WetLabRoboData/diffusion-cap-finetuned")
+```
+
+## Provenance
+
+Reorganized from `WetLabRoboData/lerobot-data-rama-lbm_finetune_cap` 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.