Views
No views yet
This is not a released model. It is a partial checkpoint published to exercise the publishing path. Do not cite a success rate from it - there isn't one.
| Training step | 4,250 of 80,000 |
| Objective | ℓ₁ + 10·KL (ACT CVAE), total loss 0.148 at snapshot |
| Dataset | HuggingFaceVLA/libero, all four suites jointly |
| Effective batch | 256 (16 × 16 grad-accum), bf16, one RTX 3090 |
| LIBERO success rate | not measured |
| Included | Not included (rebuilt on load) |
|---|---|
| Fusion stack (26.6M) | RADIO vision tower, nvidia/C-RADIOv2-B (98.2M) |
| Action decoder (14.2M) | T5-small encoder blocks (18.9M) |
| CVAE style encoder (7.1M, training only) | |
| Projections, state encoder, pos/view embeddings | |
| Normalisation statistics and the pruned vocab map | |
| 80 rows of T5's embedding table (pruned to the LIBERO corpus) |
vision.* entries are nine floats (summary indices and the input
conditioner's mean/std). The sole pretrained weights included are 80×512 rows of
T5-small's embedding table, which is Apache-2.0.pip install "microvla[libero] @ git+https://github.com/khanhnd61-vr/microvla"1from microvla import checkpoint
2
3model, meta = checkpoint.load("best.pt", device="cuda")
4model.eval()
5print(meta["step"]) # 4250
6
7tok = model.text.tokenize(["pick up the black bowl and place it on the plate"], device="cuda")
8chunk = model.predict_chunk(images, tok["input_ids"], tok["attention_mask"], state)
9# -> (B, 12, 7) un-normalised delta end-effector actionsimages is (B, 2, H, W, 3) uint8 in view order [wrist, top]; state is the
8-D LIBERO vector [eef_pos(3), axis_angle(3), gripper_qpos(2)].<unk> with a warning.config.yaml is the exact training configuration this checkpoint was produced
from.