Instructions to use Dimios45/yam-world-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use Dimios45/yam-world-model with LeRobot:
- Notebooks
- Google Colab
- Kaggle
| {"array_metadatas": [{"array_metadata": {"param_name": "params.decoder.Dense_0.bias", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.Dense_0.kernel", "write_shape": [16, 512], "chunk_shape": [16, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.Dense_1.bias", "write_shape": [768], "chunk_shape": [768], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.Dense_1.kernel", "write_shape": [512, 768], "chunk_shape": [512, 768], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_0.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_1.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_2.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_3.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_4.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_5.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_6.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.TransformerBlock_7.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.SpatioTemporalTransformer_0.final_norm.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.decoder.image_tokens", "write_shape": [108, 512], "chunk_shape": [108, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Dense_0.bias", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Dense_0.kernel", "write_shape": [768, 512], "chunk_shape": [768, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Dense_1.bias", "write_shape": [16], "chunk_shape": [16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.Dense_1.kernel", "write_shape": [512, 16], "chunk_shape": [512, 16], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_0.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_1.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_2.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_3.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_4.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_5.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_6.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.Dense_0.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.Dense_1.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.Dense_2.kernel", "write_shape": [512, 128], "chunk_shape": [512, 128], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.Dense_3.kernel", "write_shape": [512, 512], "chunk_shape": [512, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.RMSNorm_0.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.Attention_0.RMSNorm_1.scale", "write_shape": [64], "chunk_shape": [64], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.RMSNorm_0.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.RMSNorm_1.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.SwiGLU_0.Dense_0.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.SwiGLU_0.Dense_1.kernel", "write_shape": [512, 1536], "chunk_shape": [512, 1536], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.TransformerBlock_7.SwiGLU_0.Dense_2.kernel", "write_shape": [1536, 512], "chunk_shape": [1536, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.SpatioTemporalTransformer_0.final_norm.scale", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.latent_tokens", "write_shape": [96, 512], "chunk_shape": [96, 512], "ext_metadata": null}}, {"array_metadata": {"param_name": "params.encoder.mask_token", "write_shape": [512], "chunk_shape": [512], "ext_metadata": null}}]} |