CoolFace
Modelpublic

Dexmal/DM05-Table30v2-ALOHA

sourceHugging Facegemmaupdated 2mo agoView on Hugging Face
0likes23downloads
Model Card

DM05-ALOHA (RoboChallenge)

DM0.5

<p align="center"> <a href="https://www.dexmal.com/blog/dm0.5/indexen.html"><img src="https://img.shields.io/badge/📖-TechBlog-blue" alt="Tech Blog"></a> <a href="https://github.com/dexmal/opendm"><img src="https://img.shields.io/badge/GitHub-OpenDM-181717?logo=github" alt="GitHub"></a> <a href="https://huggingface.co/datasets/RoboChallenge/Table30v2"><img src="https://img.shields.io/badge/Dataset-Table30v2-0EA5E9?logo=huggingface" alt="Table30v2 Dataset"></a> <a href="https://maas.dexmal.com/"><img src="https://img.shields.io/badge/MaaS-Online-brightgreen.svg" alt="MaaS"></a> </p>

OpenDM-format BF16 checkpoint for ALOHA on RoboChallenge Table 30 v2. Use with OpenDM third_party/robochallenge_inference (configs/generalist/aloha.yaml). See the DM05 RoboChallenge Table 30 v2 Inference Guide.

Weights: BF16 model.safetensors.

Model Card

FieldValue
Configgeneralist/aloha
Env varsALOHA_CHECKPOINT / ALOHA_NORM_STATS
OpenDM robot_typeAloha
ControlJoint relative
CamerasHead / Left wrist / Right wrist
Platform camscam_high → image0, `camleftwrist` → image1, cam_right_wrist → image_2
Native state / action stats14 / 14 (action-only quantile norm_stats.json)
Defaultsaction_horizon=25, is_history=false, inference_seed=0

Table30 Tasks

lint_roller_remove_dirt, pack_the_items, pack_the_toothbrush_holder, paint_jam, put_the_books_back, put_the_pencil_case_into_the_schoolbag, scoop_with_a_small_spoon, stamp_positioning, wipe_the_blackboard, wrap_with_a_soft_cloth

Per-task horizon overrides: third_party/robochallenge_inference/configs/generalist/aloha.yaml → task_overrides (e.g. put_the_books_back=15, stamp_positioning=45, wipe_the_blackboard=15).

Use with OpenDM RoboChallenge Inference

The RoboChallenge client now lives in OpenDM at third_party/robochallenge_inference (configs/generalist/aloha.yaml). See the DM05 RoboChallenge Table 30 v2 Inference Guide.

bash
# From the OpenDM repository root.
export OPENDM_ROOT=/path/to/opendm
pip install -e ".[fast-infer]"

cd third_party/robochallenge_inference
export ALOHA_CHECKPOINT=/path/to/DM05-ALOHA
export ALOHA_NORM_STATS=${ALOHA_CHECKPOINT}/norm_stats.json
pip install -r requirements.txt

python execute.py --config-name generalist/aloha \
  user_id=YOUR_USER_ID \
  submission_id=YOUR_SUBMISSION_ID

Override without env vars:

bash
python execute.py --config-name generalist/aloha \
  checkpoint=/path/to/DM05-ALOHA \
  norm_stats=/path/to/DM05-ALOHA/norm_stats.json \
  user_id=YOUR_USER_ID \
  submission_id=YOUR_SUBMISSION_ID

If ALOHA_NORM_STATS is unset, the client falls back to ${ALOHA_CHECKPOINT}/norm_stats.json.

Runtime Profile

From third_party/robochallenge_inference/configs/default.yaml → robot_profiles.aloha:

  • —action_type=joint, action_mode=relative
  • —is_history=false, add_state=true, speed=0.5
  • —inference_seed=0, resize_name=padding

Files

text
.
├── config.json
├── model.safetensors
├── norm_stats.json
├── tokenizer.json
├── tokenizer_config.json
├── processor_config.json
├── chat_template.jinja
├── generation_config.json
└── README.md

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}
}