Overworld
/

owl-idm-v0-tiny

inverse-dynamics-model

computer-vision

Model card Files Files and versions

shahbuland commited on Feb 4

Commit

2b0f0d6

·

verified ·

1 Parent(s): 8942ffb

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -23,8 +23,8 @@ This model predicts player controls from visual observations:
 - **Backbone**: Spatial Conv3D encoder → Temporal Transformer
 - **Window size**: 8 frames
-- **Model size**: N/A parameters
-- **Inference speed**: ~1500+ FPS on single GPU
 ## Training

 - **Backbone**: Spatial Conv3D encoder → Temporal Transformer
 - **Window size**: 8 frames
+- **Model size**: 70M parameters
+- **Inference speed**: ~1500 FPS on H100 GPU
 ## Training