---
license: gemma
library_name: transformers
base_model:
- Dexmal/DM05
datasets:
- Dexmal/vla_arena_L0_L
tags:
- robotics
- robot-control
- vision-language-action
- vla
- dm05
- dm0.5
- vla-arena
- opendm
---
# DM05-vla-arena
## Introduction
DM05-vla-arena is the VLA-Arena 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.
#### VLA-Arena Results
| Method | Metric | L0 | L1 | L2 |
| --- | --- | ---: | ---: | ---: |
| DM0.5 | SR | 89.0% | 53.6% | 44.1% |
| | CC | 1.9 | 18.75 | 22.52 |
## 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 .
```
## VLA-Arena Testing
Use the VLA-Arena-specific experiment configuration when evaluating this
checkpoint. The inference service and evaluation client run separately and
communicate over HTTP.
For the complete training and evaluation workflow, see the
[DM05 VLA-Arena Training and Evaluation Guide](https://github.com/dexmal/opendm/blob/main/docs/en/dm05_vla_arena.md).
### Start the VLA-Arena Inference Service
Run this command from the OpenDM repository root. The checkpoint must contain
the matching `norm_stats.json`.
```bash
script/dm05_launcher.sh \
--exp playground/dm05_vla_arena.py \
--task inference \
--nproc_per_node 1 \
--model-config.model-name-or-path ./checkpoints/DM05-vla-arena-bf16 \
--inference-config.output-action-dim 7
```
Keep the service running while executing the benchmark.
### Prepare the VLA-Arena Evaluation Client
```bash
git clone https://github.com/PKU-Alignment/VLA-Arena
cd VLA-Arena
```
Install the VLA-Arena dependencies:
```bash
sudo apt-get install -y libosmesa6-dev libglfw3 libgl1-mesa-glx libglib2.0-0
pip install robosuite==1.5.1 bddl numpy==1.26.4 requests tqdm pyyaml "imageio[ffmpeg]" pillow
pip install -e .
export MUJOCO_GL=osmesa
```
Copy the evaluation files from the OpenDM repository:
```bash
mkdir -p vla_arena/models/DM05
# Copy evaluation files from the OpenDM repository
cp /third_party/vla_arena/eval.py vla_arena/models/DM05/eval.py
cp /third_party/vla_arena/eval_config.yaml vla_arena/models/DM05/eval_config.yaml
```
Edit `vla_arena/models/DM05/eval_config.yaml` so that `server_url` points to
the running inference service:
```yaml
server_url: "http://:7891/process_frame"
request_timeout: 30
action_horizon: 20
replan_steps: 10
robot_type: "Franka"
batch_size: 1
speed: "0.5"
# "all" evaluates all 170 tasks (11 suites × 3 levels)
task_suite_name: "all"
task_level: 0
num_trials_per_task: 10
seeds: [7, 42, 1000]
model_name: "DM05"
local_log_dir: "./experiments/eval_results"
save_video_mode: "first_success_failure"
```
### Run the VLA-Arena Benchmark
From the VLA-Arena repository root, run:
```bash
python -m vla_arena.models.DM05.eval \
--config vla_arena/models/DM05/eval_config.yaml \
--output-dir ./experiments/eval_results
```
Evaluation artifacts are written under `/seed_/`, including
`results_.json`, `tasks_.csv`, and rollout videos under
`videos/`.
## 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 [](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}
}
@misc{zhang2025vlaarena,
title = {VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models},
author = {Borong Zhang and Jiahao Li and Jiachen Shen and Yishuai Cai and Yuhao Zhang and Yuanpei Chen and Juntao Dai and Jiaming Ji and Yaodong Yang},
year = {2025},
eprint = {2512.22539},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2512.22539},
}
```