Downloads · 30 days
0
pi05-taco-libero32-checkpoints
Berkeley-ICON-Lab/pi05-taco-libero32-checkpoints
pi05-taco-libero32-checkpoints is a robotics model from Berkeley-ICON-Lab. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for jax.
This repository archives the 36 checkpoints referenced by the final Pretrain-32 LIBERO evaluation manifest. It includes the pretrained model and the SFT, RETAIN (alpha=0.9), LoRA, legacy EWC, L2 All, TACO All, and sta…
Access
Public
Updated Aug 27, 2026
Repo size
954 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other954 GB · 100%
At a glance
- Task
- Robotics
- Library
- jax
- Access
- Public
- Created
- Aug 27, 2026
- Updated
- Aug 27, 2026
- SHA
- 6b8a613f
Model card
From the Hugging Face model README
pi0.5 TACO LIBERO-32 Checkpoints
This repository archives the 36 checkpoints referenced by the final Pretrain-32 LIBERO evaluation manifest. It includes the pretrained model and the SFT, RETAIN (alpha=0.9), LoRA, legacy EWC, L2 All, TACO All, and standard WTACO checkpoints for the single-task and sequential experiments.
Each checkpoint is stored under checkpoints/<tag>/. Full training state is
retained when it exists so that experiments can be resumed. manifest.tsv
maps each tag to its experiment, method, OpenPI config, and focus task IDs.
The associated 5-seed x 10-episode evaluation artifacts are stored in the
Berkeley-ICON-Lab/pi05-taco-libero32-evals dataset repository.
These checkpoints use the Orbax layout expected by the accompanying OpenPI code. See the evaluation repository for the exact scripts and code revision.
- Task
- Robotics
- Library
- jax
- Created
- Aug 27, 2026
- Updated
- Aug 27, 2026