Smolvla So100 Stack Cube
Smolvla So100 Stack Cube is a model hosted on Hugging Face, categorized under robotics. The evidence indicates that it is associated with LeRobot, a robotics library, and can be used for tasks related to robotics policies. The model is distributed in the safetensors format and is available under the Apache-2.0 license. Users are provided with instructions for integrating the model with LeRobot, including commands for fine-tuning the model on custom datasets and running the policy using the record function. The evidence references an arXiv paper (arxiv: 2506.01844), suggesting a research context, but does not provide further details about the model's architecture or specific use cases. Access is provided via Hugging Face, and the model can be used with various libraries, inference providers, notebooks, and local applications as indicated by the general instructions. No information is provided about pricing, target user roles, or specific capabilities beyond its connection to robotics and LeRobot.
Overview
5 featuresIn the Quantised & converted weights space, Smolvla So100 Stack Cube takes a focused approach. It provides a ready-to-use robotics policy model for cube stacking tasks using imitation learning. It is built as an open-source project for robotics researchers and developers. Smolvla So100 Stack Cube is open source under the Apache-2.0 license. It ships for the command line, and it can be self-hosted.
majinwakeup30 builds and maintains Smolvla So100 Stack Cube, and it first shipped in 2024. The project is developed in the open on GitHub with 25.7k stars and 168 commits in the last 90 days. Among its 5 catalogued features are robotics policy, cube stacking, and imitation learning.
Summary written by a language model from the project’s public pages.
- Robotics policy
- Cube stacking
- Imitation learning
- Open source weights
- Local inference
Built with & integrations
- AWS
- x-amz-cf-id header · x-amz-cf-pop header · via header
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed11 Jul · 14:59 UTCmajinwakeup30/smolvla_so100_stack_cube_v1 verified via Hugging Face EnumeratorSource: Hugging Face Enumerator · Open
Frequently asked questions about Smolvla So100 Stack Cube
- What does Smolvla So100 Stack Cube do?
- Smolvla So100 Stack Cube provides a ready-to-use robotics policy model for cube stacking tasks using imitation learning. It is catalogued under Quantised & converted weights on PulseGate.
- Who should use Smolvla So100 Stack Cube?
- Smolvla So100 Stack Cube is an open-source project built for robotics researchers and developers.
- Does Smolvla So100 Stack Cube have a free plan?
- Yes — Smolvla So100 Stack Cube is open source under the Apache-2.0 license and free to use.
- What platforms does Smolvla So100 Stack Cube run on?
- Smolvla So100 Stack Cube runs on the command line. It can also be self-hosted.
- Is Smolvla So100 Stack Cube still active?
- The GitHub repository shows 168 commits in the last 90 days.
- Who makes Smolvla So100 Stack Cube?
- Smolvla So100 Stack Cube is developed by majinwakeup30.
- How long has Smolvla So100 Stack Cube been around?
- Smolvla So100 Stack Cube first shipped in 2024.
- Is Smolvla So100 Stack Cube open source?
- Yes — Smolvla So100 Stack Cube is open source under the Apache-2.0 license.
Similar projects
Closest matches by what these projects do