Embodied · vla · vla.action_prediction · vla.policy_rollout · robot_policy · subtask_prediction

GigaBrain-0

open-gigaai

WorldFoundry in-tree GigaBrain-0.1 runtime emitted a checkpoint-backed CUDA action_trace using converted LeRobot RobotWin stats.

Runner verifiedUnified environmentgiga-brain-0

Build your run

Choose a recorded variant, then copy the exact setup or inspection command.

worldfoundry.pipeline

Variant

Taskvla.action_prediction

Environmentworldfoundry-unified-cu128

DeviceCUDA 12.8

worldfoundry-eval evaluate \
  --mode model \
  --model-id giga-brain-0-3.5b-base \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/giga-brain-0-3.5b-base \
  --metric artifact_count \
  --json

Compatibility & versions

Manifest-backed recipe

Integration: integrated
Runner evidence: verified
Environment: worldfoundry-unified-cu128
Python: 3.11
CUDA: CUDA 12.8
PyTorch: torch
Source revision: —
Checkpoint revision: —

Runtime profile: giga-brain-0
Pipeline binding: giga-brain-0
Runner: worldfoundry.pipeline
Pipeline target: worldfoundry.pipelines.component_pipelines:GigaBrain0Pipeline
Backend stage: in_tree_runtime
Runtime status: in_tree_giga_brain_0_runtime_converted_lerobot_stats_predict_gpu_ready_non_leaderboard
Driver status: compatible
Environment kind: Unified environment

Install environment

The environment resolver reads the recorded profile and chooses the unified or dedicated environment shown here.

bash scripts/setup/model_env_install.sh --model giga-brain-0-3.5b-base

Package constraints 12

numpy
Pillow
torch
torchvision
matplotlib
PyYAML
numpydantic
tyro
transformers
accelerate
safetensors
opencv-python

Conda packages 3

python
pip
ffmpeg

Checkpoints & assets

Run the local check before allocating compute. Gated, private, and license fields below come directly from the checkpoint manifest.

worldfoundry-eval zoo model-download --model-id giga-brain-0 --check-local --json

open-gigaai/GigaBrain-0-3.5B-Base

Revision: —
License: apache-2.0
Gated: —
Private: —

open-gigaai/GigaBrain-0.1-3.5B-Base

Revision: —
License: apache-2.0
Gated: —
Private: —

google/paligemma-3b-pt-224

Revision: —
License: —
Gated: —
Private: —

physical-intelligence/fast

Revision: —
License: —
Gated: —
Private: —

Launch & outputs

The generated command uses the shared evaluation boundary and writes durable result manifests and artifacts.

worldfoundry-eval evaluate \
  --mode model \
  --model-id giga-brain-0-3.5b-base \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/giga-brain-0-3.5b-base \
  --metric artifact_count \
  --json

Input contract

Field	Recorded contract
`action_chunk`	50
`actions`	robot_action, action_chunk, continuous_action, subtask, trajectory_2d
`data_path`	lerobot_dataset
`embodiment_id`	Required
`image`	Required
`instruction`	Required
`original_action_dim`	robot_specific
`prompt`	Required
`state`	Required
`video`	Optional

Artifact contract

Artifact kind	Filename / path
`action_trace`	`—`
`action_trace`	`giga_brain_0_action_trace.json`

Evidence & sources

Catalog integration, native-demo parity, and runner parity are independent records.

Integration: integrated
Runner evidence: verified
Native demo evidence: Not recorded
Validation imports: numpy, PIL, torch, torchvision, tyro, matplotlib, yaml, transformers, accelerate, safetensors, cv2

Recipe provenance

worldfoundry/data/models/catalog/vla_va_wam/giga-brain-0.yamlGitHubhttps://github.com/open-gigaai/giga-brain-0Hugging Facehttps://huggingface.co/open-gigaai/GigaBrain-0-3.5B-BaseHugging Facehttps://huggingface.co/open-gigaai/GigaBrain-0.1-3.5B-BaseHugging Facehttps://huggingface.co/google/paligemma-3b-pt-224Hugging Facehttps://huggingface.co/physical-intelligence/fast

Build your run

Input contract

Artifact contract

Related recipes