g1_fdmV2_allTasks_1250 — LingBot-VA G1 multi-task transformer (step 1250)

Fine-tuned transformer for LingBot-VA on Unitree G1 (Dex1), joint 5-task post-train on JingwuLuo/all_tasks_lerobot (300 episodes across 5 tasks).

• Base: robbyant/lingbot-va-base
• Post-training: 300 demos / 5 tasks (one multi-task fine-tune), lr 1e-5, FDM v2 recipe — mutually-exclusive per-microstep regime (rank-synced coin fdm_prob=0.5: FDM video-only L_fdm Eq.13 lambda_fdm=1.0 OR standard IDM L_dyn+L_inv; one forward, one backward).
• Optimizer step 1250 of a 5000-step schedule — early/partial checkpoint (the run stopped at 1250 before completion). Useful for early eval; expect better with a finished 5000-step run.
• This repo contains only transformer/ — vae/, text_encoder/, tokenizer/ are unchanged from robbyant/lingbot-va-base.

Tasks covered (instruction strings used during training)

slug	instruction
open_lid_add_potato	Open the pot's lid and put the potato inside the pot.
pick_red_bottle	Pick up the red bottle
pick_and_move_bottle	Pick the pink object and put it on the cross mark.
put_carrot_n_cup	Pick up the carrot and put it inside the blue cup, then put the cup on the cross mark.
put_cup_n_broccoli	Pick the pink object and put it in the orange basket, then pick up the broccoli and put it inside the pink object.

Assemble an eval-ready checkpoint

hf download robbyant/lingbot-va-base                   --local-dir lingbot-va-base
hf download armanakbari4/g1_fdmV2_allTasks_1250        --local-dir alltasks_1250_dl

mkdir -p g1_alltasks_1250
ln -sf $(realpath alltasks_1250_dl/transformer)  g1_alltasks_1250/transformer
ln -sf $(realpath lingbot-va-base/vae)           g1_alltasks_1250/vae
ln -sf $(realpath lingbot-va-base/text_encoder)  g1_alltasks_1250/text_encoder
ln -sf $(realpath lingbot-va-base/tokenizer)     g1_alltasks_1250/tokenizer

Serve with CONFIG_NAME=g1_alltasks MODEL_PATH=g1_alltasks_1250. Use the same instruction string per task as the training table above. transformer/config.json has attn_mode: torch (inference-ready).