Downloads · 30 days
2
5% of all-time downloads
makermods/smolvla_makermods_100_ep_blue_cube_orange_box_2026-08-04_20-03-25
smolvla_makermods_100_ep_blue_cube_orange_box_2026-08-04_20-03-25 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 is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
Downloads · 30 days
2
5% of all-time downloads
All-time downloads
38
Public
Parameters
450M
3.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.6 GB · 100%
How the weights are stored.
BF16301M · 67%
From the Hugging Face model README
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
<p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/640e21ef3c82bd463ee5a76d/aooU0a3DMtYmy_1IWMaIM.png" alt="smolvla architecture" width="85%"/> </p> <!-- A short demo is worth more than any description! Record a GIF/video of the policy running on your robot, upload it to this repo, and embed it here: <p align="center"> <img src="https://huggingface.co/makermods/smolvla_makermods_100_ep_blue_cube_orange_box_2026-08-04_20-03-25/resolve/main/demo.gif" width="60%"/> </p> -->This policy has been trained and pushed to the Hub using LeRobot.
Learn how to train and run it in the LeRobot smolvla guide, or browse the full documentation.
so_followerwrist, frontThis checkpoint is the step 40000 (final) checkpoint of the run
smolvla_makermods_100_ep_blue_cube_orange_box_2026-08-04_20-03-25. It continues
training on the same dataset for a further 40000 steps beyond the 10000-step
Aug-03 checkpoint, giving 50000 cumulative steps of fine-tuning on
makermods/100_ep_blue_cube_orange_box.
The policy consumes these observation features and produces these action features.
Inputs
| Feature | Type | Shape |
|---|---|---|
observation.state | STATE | (6,) |
observation.images.wrist | VISUAL | (3, 480, 640) |
observation.images.front | VISUAL | (3, 480, 640) |
Outputs
| Feature | Type | Shape |
|---|---|---|
action | ACTION | (6,) |
| Setting | Value |
|---|---|
| Training steps | 40000 |
| Batch size | 8 |
| Optimizer | adamw |
| Learning rate | 0.0001 |
| Weight decay | 1e-10 |
| Grad clip norm | 10 |
| LR warmup steps | 1000 |
| LR decay steps | 30000 |
| Final LR | 2.5e-06 |
| Seed | 1000 |
| Freeze vision encoder | true |
| Train expert only | true |
| Chunk size / action steps | 50 / 50 |
| LeRobot version | 0.6.0 |
Final training loss: 0.095 (grad norm 1.582). Training completed in ~1h35m on a single RTX 4090.
New to LeRobot? These guides cover the full workflow:
lerobot package.lerobot-* commands.The short version to run and train this policy:
lerobot-rollout \
--strategy.type=base \
--robot.type=so_follower \
--robot.port=<your_robot_port> \
--robot.cameras="{ wrist: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}, front: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}}" \
--policy.path=makermods/smolvla_makermods_100_ep_blue_cube_orange_box_2026-08-04_20-03-25 \
--task="pick up blue cube and place it in orange box" \
--duration=60
Replace the remaining <...> placeholders with your own values: --robot.port and the camera indices are specific to your machine. The camera names wrist and front must be kept as-is — they match the observation keys this policy was trained on.
When --strategy.type=base is used the script doesn't record the episodes. Skipping duration will make the policy run indefinitely. For more information look at rollout documentation.
lerobot-train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.path=makermods/smolvla_makermods_100_ep_blue_cube_orange_box_2026-08-04_20-03-25 \
--output_dir=outputs/train/<policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<policy_repo_id> \
--wandb.enable=true
Writes checkpoints to outputs/train/<policy_repo_id>/checkpoints/.
No evaluation results have been provided for this policy yet.
If you use this policy, please cite the method linked in the description above, along with LeRobot:
@misc{cadene2024lerobot,
author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
howpublished = "\url{https://github.com/huggingface/lerobot}",
year = {2024}
}