Downloads · 30 days
40
100% of all-time downloads
pi05-eUiSKJr4zg3Q
ml-developers/pi05-eUiSKJr4zg3Q
pi05-eUiSKJr4zg3Q is a robotics model from ml-developers. Use it for the robotics task on the model card, and read the license before you ship it in a product.
Canonical parent (per the OpenRoboto Model Originality policy): openroboto-ai/champion@d54728aa7347c2996fe1545cc75d2055909458b0 (official champion snapshot, mirror of ApexUltron/pi05-KsYerY3Q8siH@4ac5fea918107a26ba525…
All-time downloads
40
Public
Parameters
6.4B
25.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors25.5 GB · 100%
At a glance
- Task
- Robotics
- Model type
- lingbotvla
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- 08fd846c
Base models
Model card
From the Hugging Face model README
LingBot-VLA 2.0 — expert-only fine-tune (SN80 competition 2)
Canonical parent (per the OpenRoboto Model Originality policy):
openroboto-ai/champion@d54728aa7347c2996fe1545cc75d2055909458b0
(official champion snapshot, mirror of ApexUltron/pi05-KsYerY3Q8siH@4ac5fea918107a26ba525e3d1b6bdbe615d4ee72).
Training method: continued training with train_expert_only=true — the entire
Qwen3-VL backbone (vision tower, all 36 LLM layers, embeddings) frozen and
byte-identical to the parent; gradients applied only to the MoE action expert,
action/state/time projections, and align heads. 2,000 steps, muon, lr 3e-6 -> 3e-7
cosine, global batch 64, fp32.
Data: LIBERO demonstrations (lerobot/libero) plus successes-only policy rollouts collected on randomized layouts of the four TRAINING suites (no evaluation-suite BDDL files or init states were used).
- Task
- Robotics
- Type
- lingbotvla
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026