VLA training framework.
Project description
Starlord
Dual system training framework for robotics.
The overall structure borrowed from GR00T, with these modifications:
- Simplifer VLM model, introduced more advanced VLM and larger slow system;
- Connecting fast system without cross-attention, using text encoder instead;
Slow thought system
will goes starlord/model/backbone contains various VLMs. Provides a unified interface connect with fast system (action expert)
Fast action system
Currently support:
- DiT: diffusion transformer
- QwenFlow: flowmatching based action expert
Training
training scripts goes to scripts/xxx.sh
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
starlord_twin-0.0.1.tar.gz
(54.9 kB
view details)
File details
Details for the file starlord_twin-0.0.1.tar.gz.
File metadata
- Download URL: starlord_twin-0.0.1.tar.gz
- Upload date:
- Size: 54.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e37d0a3e6467f5cdf9aed6b3f568e46b8dbf6fbc09b2e292ec98151341b0bc43
|
|
| MD5 |
63e8907949aef29f0ec77279a635710d
|
|
| BLAKE2b-256 |
64f12462a6d064b522f00d3888f5b4cfab91e2ea9396a68ea7beb90d3f0851a2
|
