Downloads Β· 30 days
44
57% of all-time downloads
Dexmal/DM05-Table30v2-ALOHA
DM05-Table30v2-ALOHA is a robotics model from Dexmal. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.
Downloads Β· 30 days
44
57% of all-time downloads
All-time downloads
77
Public
Parameters
5.8B
11.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors11.7 GB Β· 100%
From the Hugging Face model README

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.
| Field | Value |
|---|---|
| Config | generalist/aloha |
| Env vars | ALOHA_CHECKPOINT / ALOHA_NORM_STATS |
OpenDM robot_type | Aloha |
| Control | Joint relative |
| Cameras | Head / Left wrist / Right wrist |
| Platform cams | cam_high β image_0, cam_left_wrist β image_1, cam_right_wrist β image_2 |
| Native state / action stats | 14 / 14 (action-only quantile norm_stats.json) |
| Defaults | action_horizon=25, is_history=false, inference_seed=0 |
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 β task_overrides
(e.g. put_the_books_back=15, stamp_positioning=45, wipe_the_blackboard=15).
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.
# 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:
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.
From third_party/robochallenge_inference/configs/default.yaml β robot_profiles.aloha:
action_type=joint, action_mode=relativeis_history=false, add_state=true, speed=0.5inference_seed=0, resize_name=padding.
βββ config.json
βββ model.safetensors
βββ norm_stats.json
βββ tokenizer.json
βββ tokenizer_config.json
βββ processor_config.json
βββ chat_template.jinja
βββ generation_config.json
βββ README.md
@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}
}