Being-H0.5 Base โ€” LeRobot conversion

This is a deterministic LeRobot-format conversion of BeingBeyond/Being-H05-2B. It contains the policy configuration, serialized preprocessor and postprocessor pipelines, tokenizer, conversion report, and safetensors weights.

Revisions

  • Author source: ab1204954cb5e68f0bc52a376982e962c763bbbe
  • Source checkpoint: bb31ffcf7d67a8d5ec82d715d5e1678581ef6374
  • LeRobot integration: 27152836dab56f5e6b1cecd3fa62f45bbd4e274d

Validation

  • 990 source tensors mapped to 1,086 native-layout tensors
  • Native LeRobot policy using Transformers Qwen3 primitives and InternVLVisionModel
  • 0 missing, unexpected, duplicate, or shape-mismatched tensors
  • Strict offline save/reload passed
  • Strict native-policy reload on an RTX 5090 passed
  • SHA-256: aa0bebd77092dfe9e53afec8e0b25e07f3b9175c45bc795e3851dad1dedff530
  • Author-vs-LeRobot fixed-noise flow velocity/loss and sampled action at batch sizes 1 and 2: maximum and p99 absolute error 0

The checkpoint preserves Being-H0.5's fixed semantic 200D state/action slots, validity masks, three-camera processing, raw task string, and four-step flow-matching sampler. It consumes the named state and action fields from the released model contract; an environment-specific vector adapter is not included.

Usage

Install LeRobot with the Being-H0.5 extra:

pip install -e ".[being_h05]"

No author-source checkout or PYTHONPATH change is required. Load the checkpoint as a standard LeRobot policy:

lerobot-eval --policy.path=lerobot/being_h05_base
Downloads last month
179
Safetensors
Model size
3B params
Tensor type
F32
ยท
Video Preview
loading

Model tree for lerobot/being_h05_base

Unable to build the model tree, the base model loops to the model itself. Learn more.