Downloads · 30 days
0
SmolVLA-SewerBot-v0
saralsystems/SmolVLA-SewerBot-v0
SmolVLA-SewerBot-v0 is a robotics model from saralsystems. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
First Vision Language Action (VLA) model for confined spaces, such as cleaning sewer tanks in India.
Access
Public
Updated Mar 12, 2026
Repo size
425 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt425 KB · 99%
At a glance
- Task
- Robotics
- License
- apache-2.0
- Access
- Public
- Created
- Mar 12, 2026
- Updated
- Mar 12, 2026
- SHA
- 9e1faf03
Model card
From the Hugging Face model README
SmolVLA-SewerBot-v0 (Phase 0 Stub)
First Vision Language Action (VLA) model for confined spaces, such as cleaning sewer tanks in India.
This is NOT a production model. Work in progress, more details coming soon.
Architecture
- Base: Stub 4-layer MLP (state -> action), NOT SmolVLA
- Input: 18-dim proprioceptive state (joint_pos + joint_vel + ee_pos + ee_quat + base_pos)
- Output: 7-DOF action
- Parameters: ~105K total
- Training: 20 steps, MSE loss, Adam optimizer
Intended Use
Pipeline validation only. Do not deploy on a real robot.
Source
- GitHub: saralsystems/sewer-vla
- Dataset: sewer-vla-mujoco-v0
- License: Apache 2.0
- Task
- Robotics
- License
- apache-2.0
- Created
- Mar 12, 2026
- Updated
- Mar 12, 2026