SmolVLA (rm65b stack blocks)
LeRobot policy checkpoints uploaded by goal_gen/upload_hf_checkpoints.sh.
Each subfolder contains the deployment-ready pretrained_model/ payload
(model.safetensors + config.json + pre/postprocessor + train_config.json).
| Subfolder | Train step | Final train loss |
|---|---|---|
checkpoint-050000 |
50,000 | 0.040 |
Usage
from huggingface_hub import snapshot_download
ckpt_dir = snapshot_download(
"JayCao99/smolvla-rm65b-stack-v0.0",
allow_patterns="checkpoint-050000/*",
)
from lerobot.policies.smolvla.modeling_smolvla import SmolVLAPolicy
policy = SmolVLAPolicy.from_pretrained(f"{ckpt_dir}/checkpoint-050000")