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

MolmoAct2

allenai

WorldFoundry in-tree MolmoAct2 runtime lives under worldfoundry/synthesis/action_generation/molmoact2 and no longer depends on the external molmoact2 checkout at runtime.

Runner verifiedUnified environmentmolmoact2

Build your run

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

worldfoundry.pipeline
Taskvla.policy_rollout
Environmentworldfoundry-unified-cu128
DeviceCUDA 12.8
worldfoundry-eval evaluate \
  --mode model \
  --model-id molmoact2-droid \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/molmoact2-droid \
  --metric artifact_count \
  --json
01

Compatibility & versions

Manifest-backed recipe

Integration
in tree checkpoint runtime static verified
Runner evidence
verified
Environment
worldfoundry-unified-cu128
Python
3.11
CUDA
CUDA 12.8
PyTorch
torch
Source revision
Checkpoint revision
Runtime profile
molmoact2
Pipeline binding
molmoact2
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.component_pipelines:MolmoAct2Pipeline
Backend stage
in_tree_runtime
Runtime status
in_tree_molmoact2_hf_predict_action_gpu_validated
Driver status
compatible
Environment kind
Unified environment
02

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 molmoact2-droid
Package constraints 10
  • torch
  • torchvision
  • transformers>=4.57,<4.58
  • accelerate>=1.0
  • safetensors>=0.4
  • pillow>=10
  • numpy>=1.26,<3
  • einops>=0.7
  • sentencepiece>=0.2
  • protobuf>=4.25
Conda packages 2
  • python
  • pip
03

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 molmoact2 --check-local --json
allenai/MolmoAct2-DROID
Revision
License
apache-2.0
Gated
Private
allenai/MolmoAct2-BimanualYAM
Revision
License
apache-2.0
Gated
Private
allenai/MolmoAct2-SO100_101
Revision
License
apache-2.0
Gated
Private
allenai/MolmoAct2-LIBERO
Revision
License
apache-2.0
Gated
Private
allenai/MolmoAct2-Think-LIBERO
Revision
License
apache-2.0
Gated
Private
allenai/MolmoAct2
Revision
License
Gated
Private
allenai/MolmoAct2-Think
Revision
License
Gated
Private
04

Launch & outputs

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

worldfoundry-eval evaluate \
  --mode model \
  --model-id molmoact2-droid \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/molmoact2-droid \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
actionsaction_chunk, robot_action
camera_keysexternal_cam, external_cam_2, wrist_cam
default_embodimentdroid
imageRequired
instructionRequired
norm_tagfranka_droid
promptRequired
stateRequired
state_dim8
videoOptional

Artifact contract

Artifact kindFilename / path
action_trace
action_tracemolmoact2_action_trace.json
05

Evidence & sources

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

Integration
in tree checkpoint runtime static verified
Runner evidence
verified
Native demo evidence
Not recorded
Validation imports
numpy, PIL, torch, torchvision, transformers