StarForce
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 starforce/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
Env install
pip install -e .[base]
Training
training scripts goes to scripts/xxx.sh
training fast system:
sh scripts/v0/sl_0.sh
training slow thinking system:
1 maintainer
Metadata
1 maintainer
Release files for starforce 1.1.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| starforce-1.1.7.tar.gz | 2.0 MB | Details |
Release files / starforce-1.1.7.tar.gz
| Download URL | starforce-1.1.7.tar.gz |
|---|---|
| Size | 2.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
25288807400c8c7ec03b736550ffeff6e1112875a38ab65a50bc220604ed2041
|
|
BLAKE2b-256 checksum How to use checksums |
882524fb3e3bd4cadfa5eb10698b699c5f6af651df7a54c7540973bbe8754014
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
