Downloads · 30 days
7
10% of all-time downloads
t08_pick_and_place_policy_020000
LBST/t08_pick_and_place_policy_020000
t08_pick_and_place_policy_020000 is a robotics model from LBST. 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 lerobot.
This model is a checkpoint from the training of a pick-and-place policy using SmolVLA architecture.
All-time downloads
67
Public
Parameters
450M
907 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors907 MB · 100%
Parameter types
How the weights are stored.
BF16447M · 99%
Model card
From the Hugging Face model README
T08 Pick and Place Policy - Checkpoint 020000
This model is a checkpoint from the training of a pick-and-place policy using SmolVLA architecture.
Model Details
- Checkpoint: 020000
- Architecture: SmolVLA
- Task: Pick and Place (T08)
- Training Step: 020000
Usage
You can evaluate this model using LeRobot:
python -m lerobot.scripts.eval \
--policy.path=LBST/t08_pick_and_place_policy_020000 \
--env.type=<your_environment> \
--eval.n_episodes=10 \
--policy.device=cuda
Files
config.json: Policy configurationmodel.safetensors: Model weights in SafeTensors formattrain_config.json: Complete training configuration for reproducibility
Parent Repository
This checkpoint was extracted from: LBST/t08_pick_and_place_policy_smolvla_files
Generated automatically from checkpoint 020000
- Task
- Robotics
- Library
- lerobot
- Created
- Aug 5, 2025
- Updated
- Aug 5, 2025