lerobot / being_h05_base

Being-H0.5 Base — 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: 44c942c9bf648ea27729cae1b38eb8d33377652e

Validation

• 990 source tensors mapped to 1,086 native-layout tensors
• Transformers-native Qwen3Config and InternVLVisionModel
• 0 missing, unexpected, duplicate, or shape-mismatched tensors
• Strict offline save/reload 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.

Usage

The audited author BeingH/MoT action architecture is currently required at runtime; the Qwen configuration, tokenizer, and InternVL vision tower are provided by Transformers:

git clone https://github.com/BeingBeyond/Being-H.git
git -C Being-H checkout ab1204954cb5e68f0bc52a376982e962c763bbbe
export PYTHONPATH="$PWD/Being-H/Being-H05:$PYTHONPATH"

Then load the checkpoint as a standard LeRobot policy:

lerobot-eval --policy.path=lerobot/being_h05_base