EVO1 (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-020000 |
20,000 | 0.074 |
Usage
from huggingface_hub import snapshot_download
ckpt_dir = snapshot_download(
"JayCao99/evo1-rm65b-stack-v0.0",
allow_patterns="checkpoint-020000/*",
)
from lerobot.policies.evo1.modeling_evo1 import Evo1Policy
policy = Evo1Policy.from_pretrained(f"{ckpt_dir}/checkpoint-020000")