Downloads · 30 days
0
lingbot-va-g1
jfgpt/lingbot-va-g1
lingbot-va-g1 is a robotics model from jfgpt. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for diffusers.
Fine-tuned Wan2.2-5B diffusion transformer for the Biomech G1 dual-arm robot.
Access
Public
Updated Jun 24, 2026
Parameters
5.1B
10.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.2 GB · 100%
At a glance
- Task
- Robotics
- Library
- diffusers
- Access
- Public
- Created
- Jun 23, 2026
- Updated
- Jun 24, 2026
- SHA
- 362b8c55
Model card
From the Hugging Face model README
LingBot-VA G1 Diffusion World Model
Fine-tuned Wan2.2-5B diffusion transformer for the Biomech G1 dual-arm robot.
Model Details
- Base: Wan2.2-5B Diffusion Transformer
- Parameters: ~5.3B (5.0B video + 0.3B action expert)
- Architecture: Mixture-of-Transformers (MoT) with interleaved visual/action tokens
- Action Space: 30D (G1 robot joints)
- Visual Input: 3 cameras (head + 2 wrists), 256x320
- Training: G1-BrainCo dataset, 1,598 episodes, 5,000 steps
- Hardware: 1x A100 80GB
- Attention: flex_attention with causal masking
Usage
Load with diffusers:
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"jfgpt/lingbot-va-g1/checkpoint_step_5000/transformer",
torch_dtype=torch.bfloat16,
)
Requirements
- PyTorch 2.x + CUDA
- diffusers >= 0.35.0
- transformers
License
All rights reserved — The Robbyant Team Authors.
- Task
- Robotics
- Library
- diffusers
- Created
- Jun 23, 2026
- Updated
- Jun 24, 2026