Downloads · 30 days
7
22% of all-time downloads
act-genesis-hr-bench-qpos-abs-joint-step35000
zimplex/act-genesis-hr-bench-qpos-abs-joint-step35000
act-genesis-hr-bench-qpos-abs-joint-step35000 is a robotics model from zimplex. 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. The card lists the license as mit.
Final baseline checkpoint used to produce the genesis-hr-bench evaluation numbers (eval run full202605290220, 45-task evalv1100 set). Inference-only (lerobot pretrainedmodel/ layout: weights + config + pre/post-proces…
All-time downloads
32
Public
Parameters
51.7M
207 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors207 MB · 100%
At a glance
- Task
- Robotics
- Library
- lerobot
- License
- mit
- Access
- Public
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026
- SHA
- 6520ac07
Datasets
Model card
From the Hugging Face model README
ACT — genesis-hr-bench final checkpoint (step 35,000, qpos_abs)
Final baseline checkpoint used to produce the genesis-hr-bench evaluation
numbers (eval run full_20260529_0220, 45-task eval_v1_100 set). Inference-only
(lerobot pretrained_model/ layout: weights + config + pre/post-processors).
Provenance
| Base model | trained from scratch (no pretrained init) |
| Dataset | zhouqh/hrbench → genesis_hr_bench_lerobot_qpos_target_abs_20260526_1651 |
| Action space | qpos_abs (8-D Franka joint absolute + gripper) |
| Step | 35,000 |
| Wandb | act_genesis_hr_bench/cwc1tdbe |
| Uploaded | 2026-08-05 06:59:28 UTC |
Note. Configured for 100k steps but the final saved checkpoint is step 35000 (
checkpoints/last -> 035000). wandb run was resumed once (two local session dirs share id cwc1tdbe).
Usage (lerobot)
from lerobot.policies.factory import make_policy_from_pretrained
policy = make_policy_from_pretrained("zimplex/act-genesis-hr-bench-qpos-abs-joint-step35000", device="cuda")
policy.eval()
# Observation keys: observation.images.base_0_rgb / left_wrist_0_rgb /
# right_wrist_0_rgb (as available), observation.state. Action space: qpos_abs.
action_chunk = policy.predict_action(batch_observation)
Pair the checkpoint with the matching
qpos_absdataset variant — the normalizers andaction_dimare baked in.
- Task
- Robotics
- Library
- lerobot
- License
- mit
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026