--- license: gemma library_name: peft base_model: - Dexmal/DM05 tags: - robotics - robot-control - vision-language-action - vla - lora - dm05 - dm0.5 - so101 - opendm --- # DM05-SO101-Pick-Cube ![DM0.5](https://raw.githubusercontent.com/dexmal/opendm/main/docs/image/header.png)

Tech Blog GitHub MaaS

## Introduction DM05-SO101-Pick-Cube is the SO101 fine-tuned checkpoint of DM0.5, Dexmal's open-world Vision-Language-Action foundation model for embodied intelligence. DM0.5 uses a Gemma3 4B vision-language backbone with a 680M Action Expert to generate continuous robot actions, and is designed for natural-language manipulation, zero-shot generalization, efficient downstream fine-tuning, long-horizon historical context, robust policy behavior, and transfer across robot embodiments. This checkpoint is specifically trained for the SO101 pick cube task using LoRA fine-tuning. ## Quick Start We recommend using Docker to set up the runtime environment first, which helps avoid version mismatches across CUDA, PyTorch, flash-attn, and other dependencies on the host machine. ### Requirements ```text System requirements: Ubuntu 20.04 / 22.04 NVIDIA GPU NVIDIA Driver Docker NVIDIA Container Toolkit Conda (optional, only required for local pip installation) Recommended GPUs: RTX 4090, A100, H100, H20 8 GPUs are recommended for training, and 1 GPU is sufficient for deployment inference. ``` ### Docker Installation ```bash git clone https://github.com/dexmal/opendm.git cd opendm docker run -it --rm --gpus all --network host \ --name opendm \ --shm-size=16g \ -v "$PWD":/app/opendm \ -w /app/opendm \ dexmal/opendm:latest /bin/bash # Run from the OpenDM repository root inside the container. conda activate opendm pip install -e . ``` ### Local Installation ```bash conda create -n opendm python=3.10 -y conda activate opendm pip install torch torchvision \ --index-url https://download.pytorch.org/whl/cu128 pip install ninja packaging MAX_JOBS=2 pip install flash-attn --no-build-isolation # Enter the OpenDM repository root. cd opendm pip install -e . ``` ## SO101 Inference Use the SO101-specific experiment configuration when running inference with this checkpoint. Run this command from the OpenDM repository root: ```bash script/dm05_launcher.sh \ --exp playground/dm05_so101_lora.py \ --task inference \ --nproc_per_node 1 \ --model-config.model-name-or-path ./checkpoints/DM05-SO101-Pick-Cube \ --model-config.chunk-size 50 \ --inference-config.output-action-dim 6 \ --inference-config.image-keys images_1 images_2 \ --inference-config.port 7891 ``` For the complete training and inference workflow, see the [DM05 SO101 LoRA Training Guide](https://github.com/dexmal/opendm/blob/main/docs/en/dm05_so101_lora_training.md). ## Community and Support - Learn more about Dexmal products and model updates on the [Dexmal website](https://www.dexmal.com/). - If you encounter issues, please report them through [GitHub Issues](https://github.com/dexmal/opendm/issues). - For further discussion, scan the [WeChat QR code](https://raw.githubusercontent.com/dexmal/opendm/main/docs/image/wechat.jpeg) to contact us. We will continue to release more model weights, technical documentation, and examples. If this project is helpful to you, please consider giving us a star on GitHub [![GitHub](https://img.shields.io/github/stars/dexmal/opendm?color=5B5BD6)](https://github.com/dexmal/opendm). Your support helps us move forward. ## Citation ```bibtex @misc{dm05, title = {{DM0.5}: An Open-World Foundation Model for General-Purpose Embodied Intelligence}, author = {{Dexmal Team}}, month = {July}, year = {2026}, url = {https://www.dexmal.com/blog/dm0.5/index_en.html} } ```