Skip to content

Downloading Model Artifacts ​

When training completes or a checkpoint is exported, the model artifacts are stored in the platform's object storage. You can download them for offline analysis or to load the model in your own environment.

Prerequisites ​

RequirementDetails
RoleFAE or R&D engineer
Model stateThe model version has been registered (training completed or checkpoint exported)

Archive Contents ​

Model artifacts are provided as a .tar.gz archive. When extracted, an ACT model, for example, looks like this:

text
pick_place_v1_v20261020-01/
├── model_card.json          # Model card: lineage, dataset versions, step, model family
├── checkpoint/
│   └── model.safetensors    # Model weights
├── config.json              # Model architecture and hyperparameter snapshot
├── normalization.json       # Normalization statistics for observations and actions
├── inference.yaml           # Inference config: cameras, control frequency, action chunking
└── manifest.sha256          # Checksums for the artifact files
FilePurpose
model_card.jsonRecords the training job ID, dataset versions, model family, step, progress (for checkpoints), and export time
checkpoint/Weight files
config.jsonArchitecture parameters needed to load the model
normalization.jsonUsed at inference time to normalize observations and denormalize actions
inference.yamlInference parameters such as input cameras and control frequency
manifest.sha256Used to verify the download is complete

Files may differ slightly between model families; model_card.json is the authoritative description.

Downloading ​

  1. Go to Model Deployment → Model Management and find the model.
  2. Click Details and select the version to download.
  3. Click Download; your browser downloads the artifact archive.
  4. After the download finishes, verify its integrity:
bash
tar -xzf pick_place_v1_v20261020-01.tar.gz
cd pick_place_v1_v20261020-01
sha256sum -c manifest.sha256

The download is complete if every file reports OK.

Reading the Model Card ​

python
import json

with open("model_card.json", encoding="utf-8") as f:
    card = json.load(f)

print(card["model_family"], card["step"], card["dataset_versions"])

Usage Notes ​

  • Use the same normalization: Always use the normalization.json from the archive at inference time; otherwise the action outputs will be distorted.
  • Match cameras and frequency: The camera configuration and control frequency at inference time should match inference.yaml.
  • Validate on a robot first: We recommend completing on-robot validation through NexCore deployment and evaluation before using the model elsewhere.
  • Keep the lineage: When distributing a model, include model_card.json so its training data and version can be traced.

Common Issues ​

IssueResolution
No Download buttonYour role doesn't have download permission, or downloads are disabled by platform policy
Checksum verification failsDownload again. If it still fails, submit a support request with the model version.
Loading fails with an architecture mismatchMake sure you're using the config.json from the archive and code for the matching model family

NexCore is evolving rapidly; the latest version prevails.NexCore Docs · Embodied AI Skill Learning Platform by Lumos Robotics