Yesterday
-
Model card: drop training time from the results note
Removes the training-time sentence under the results table. Updates the README.md line in ASSET_SHA256SUMS. -
Model card: note torch.compile comparison (#3)
- Model card: note torch.compile comparison (28211e4b9e83a2c5c49696e7b4c922cadc48a589) -
Model card: link the ROCm blog, label success rate (#2)
- Model card: link the ROCm blog, label success rate (a600ee39ed0b9cae9cc8b7ba53604b7238efc956) -
Model card: results, download and launcher variables (#1)
- Model card: results, download and launcher variables (605cea68c4bf0d06aebacb0964a0ce25429f1f48)
7 days ago
-
Describe the Compact Action Expert and its intended use.
-
Add the CAE-FastWAM citation.
-
Add replay.mp4 for the model page video preview.
-
Show the LIBERO videos in the model card gallery.
-
Add LIBERO example videos.
-
Link the AMD-AGI faster-action-models repository.
-
Remove the reported success rate from the model card.
-
Rename the model card to CAE-FastWAM.
-
State that no training data was added beyond the FastWAM recipe.
-
Restore the statement that the Wan2.2 weights are fine-tuned.
-
State that the Wan2.2 weights are used unchanged.
-
State that the FastWAM LIBERO training data is used unchanged.
9 days ago
-
Add files using upload-large-folder tool
