Hugging Face's logo

ldxxx
/
ODEWorld-Goal-Predictor-LIBERO

Image-to-Video
Safetensors
odeworld
dinov2
goal-prediction
language
model_hub_mixin
pytorch_model_hub_mixin
robotics
Model card Files
xet
 Community
1

ODEWorld-Goal-Predictor-LIBERO

Language-conditioned goal predictor trained on LIBERO. This checkpoint includes the goal predictor and its DINO image and text encoders.

For installation, loading, and inference instructions, see the ODEWorld GitHub repository.

Links

Downloads last month
54
Safetensors
Model size
1.0B params
Tensor type
F32
·
Inference Providers NEW
Image-to-Video
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including ldxxx/ODEWorld-Goal-Predictor-LIBERO

Paper for ldxxx/ODEWorld-Goal-Predictor-LIBERO