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
1 maintainer
Metadata
1 maintainer
Release files for starlord-twin 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| starlord_twin-0.0.1.tar.gz | 54.9 kB | Details |
Release files / starlord_twin-0.0.1.tar.gz
| Download URL | starlord_twin-0.0.1.tar.gz |
|---|---|
| Size | 54.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e37d0a3e6467f5cdf9aed6b3f568e46b8dbf6fbc09b2e292ec98151341b0bc43
|
|
BLAKE2b-256 checksum How to use checksums |
64f12462a6d064b522f00d3888f5b4cfab91e2ea9396a68ea7beb90d3f0851a2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
