No project description provided
Project description
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:
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
starforce-1.1.4.tar.gz
(1.8 MB
view details)
File details
Details for the file starforce-1.1.4.tar.gz.
File metadata
- Download URL: starforce-1.1.4.tar.gz
- Upload date:
- Size: 1.8 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0fb4adafcee64d664648884b6aaaadb9ea1ccfbbcd35fac2875024816752e880
|
|
| MD5 |
d5cfe8499dc66886b053e579bbc33ea3
|
|
| BLAKE2b-256 |
82590284b8626a681607107593d5f7d486142aef54195047cbf3eaa692e8a4e6
|
