Skip to content
RobothecaBeta
Log in

VLA-0-Smol

  • AI model
  • Humanoids and robot learning

A fork of the LeRobot library, a PyTorch toolkit for real-world robotics covering datasets, pretrained policies and simulation environments for imitation and reinforcement learning.

Made by Robot Learning Collective.

Source on GitHub: github.com/Robot-Learning-Collective/lerobot-experiments (opens in a new tab). Facts read at commit 8e71efb (opens in a new tab).

Licenses

Code
Apache-2.0 (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit 8e71efb (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Provides pretrained robot policies, human-collected demonstration datasets and simulation environments to get started without a physical robot.
  • Loads datasets from the Hugging Face hub or local folders and serves frames as PyTorch tensors, with optional temporal frame retrieval.
  • Trains policies from the command line, reproducing reported results for Diffusion Policy on the PushT task.
  • Supports Feetech motors and supports SO-101, LeKiwi and HopeJR robot builds per its tutorials.
  • Lets users upload trained policies to the Hugging Face hub with their configuration and weights.

Written by Robotheca from the project's README (opens in a new tab) at commit 8e71efb.

Getting started

Difficulty
Intermediate
Hardware it needs, as the project states it
Python 3.10+ and PyTorch 2.2+, with ffmpeg installed; building may need cmake and build-essential on Linux.

Maintenance

Status
Maintained: a commit in the last 12 months
Newest commit
27 Dec 2025 on dev
Latest release
None published on GitHub

Checked on GitHub on 16 Oct 2026.

Links

Robots that can run it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.