Downloads · 30 days
4
9% of all-time downloads
smolvla_3cam_200ep_blue_cube_orange_tray
makermods/smolvla_3cam_200ep_blue_cube_orange_tray
smolvla_3cam_200ep_blue_cube_orange_tray is a robotics model from makermods. 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 apache-2.0.
SmolVLA fine-tuned from lerobot/smolvlabase on makermods/3cam200epbluecubeorangetray — an SO-101 (6-DoF) pick-and-place: "pick up blue cube and place in orange tray".
All-time downloads
47
Public
Parameters
450M
26.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors27.3 GB · 100%
Parameter types
How the weights are stored.
BF16447M · 99%
Model card
From the Hugging Face model README
smolvla_3cam_200ep_blue_cube_orange_tray
SmolVLA fine-tuned from lerobot/smolvla_base
on makermods/3cam_200ep_blue_cube_orange_tray
— an SO-101 (6-DoF) pick-and-place: "pick up blue cube and place in orange tray".
Cameras
Three views, declared under their real mount names:
| key | resolution |
|---|---|
observation.images.front | 480x640 |
observation.images.wrist | 480x640 |
observation.images.top | 480x640 |
The base ships placeholder slots (camera1/2/3) and training used --rename_map to bind
the real mounts onto them. Both were rewritten to the real names here, and the
rename_map cleared, so no --rename_map is needed at inference — feed
front/wrist/top directly. (lerobot-eval, lerobot-rollout and the async policy
server all override a checkpoint's saved rename map with their own, which defaults to
empty, so a checkpoint left on the placeholder keys fails there.)
Training
| steps | 20,000 (batch 64 → 32.8 epochs over 38,975 frames) |
| optimizer | AdamW, lr 1e-4, betas (0.9, 0.95), wd 1e-10, grad clip 10 |
| schedule | cosine, 1,000 warmup → 2.5e-6 at step 20,000 |
| final loss | 0.045 (grad norm 0.78) |
| trainable | 100M of 450M — frozen vision encoder, action expert only |
| hardware | RTX 4090, bf16 AMP, 19.9 GB, ~5 h |
checkpoints/<step>/ holds every 1,000-step checkpoint, each git-tagged by step, so any
can be loaded with --policy.pretrained_revision=<step>.
- Task
- Robotics
- Library
- lerobot
- License
- apache-2.0
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026