RoboBrain-X0-FlagOS / README.md
YummyYum's picture
Update README.md
120909c verified
# Quick Start
## Download Model Ckpts
You should download RoboBrain-X0's weights to /share/
## Pull Docker Image
```sh
docker pull harbor.baai.ac.cn/flagrelease-public/robobrain_x0_flagscale
```
You can use cuda12.4.1-cudnn9.5.0-python3.12-torch2.6.0-time250928-ssh tag for now.
## Run Container
```sh
docker run -itd --name robotics_pretrain --privileged --gpus all --net=host --ipc=host --device=/dev/infiniband --shm-size 512g --ulimit memlock=-1 -v /share/:/models harbor.baai.ac.cn/flagrelease-public/robobrain_x0_flagscale
```
## Train
```sh
cd /root/robotics_pretrain/flag-scale
conda activate flagscale-train
python run.py --config-path ./examples/qwen2_5_vl/conf --config-name train_3b_action_S6_subtask_agilex_eval5_demo action=run
```
## Serve & Inference
```sh
cd /root/robotics_pretrain/flag-scale
conda activate flagscale-inference
python run.py --config-path ./examples/qwen2_5_vl/conf/ --config-name serve_3b action=run
```
# For more information
You can refer to the origin repo of RoboBrain-X0 https://github.com/FlagOpen/RoboBrain-X0.
The weight files and evaluation results will be released at a later date after the native model is officially launched.