IDEAS-Lab-Northwestern/lingbot-vla2-datagen-v1-stack-joint-2cam-yanZ

LingBot-VLA 2.0 — ManiGuard datagen-v1 stack (joint, 2-cam)

LingBot-VLA 2.0 post-trained on the ManiGuard stack family, one of five base models evaluated on ManiGuard-Bench under identical data, cameras, and controller.

• Warm start: robbyant/lingbot-vla-v2-6b — the pretrain release (not the RoboTwin post-trained variant).
• Data: IDEAS-Lab-Northwestern/datagen-stack-v1-joint-5cam (LeRobot v2.1, consumed directly — no format conversion).
• Inputs: 2 cameras (camera_top = the left overview, camera_wrist_left = wrist), 8-D joint state (7 arm + gripper) mapped into the 55-D unified vector.
• Actions: absolute joint targets (subtract_state: false on both features, per LingBot's own simulation recipe) — apply directly to a JointController, no delta step.
• Recipe: upstream post-training config unchanged (MoE + depth/DINO distillation on); global batch 256 = micro 32 x 8 GPUs, lr 5e-5 cosine, 2 epochs (20,750 steps).
• Ladder: checkpoints every 5,188 steps.

Files needed to serve

Everything a rollout needs is in this repo:

Path	What it is
maniguard/norm_stats.json	this family's normalization statistics
maniguard/robot_config.yaml	the feature mapping the policy was trained with; its norm_stats: points at the file above
vlm/config.json	the Qwen/Qwen3-VL-4B-Instruct config (Apache-2.0), vendored unchanged — LingBot builds the VLM skeleton from it before loading these weights
tokenizer*.json, *preprocessor_config.json, merges.txt, vocab.json, added_tokens.json, special_tokens_map.json, chat_template.jinja	the processor / tokenizer, byte-identical to training

Serve it with ManiGuard's shim, which reads all of the above from the checkpoint directory and passes the norm statistics explicitly:

python maniguard/serve/lingbot_native.py \
    --checkpoint <this repo, downloaded> --qwen-config <dir holding vlm/config.json> \
    --device cuda:0 --port 8000