{ "architectures": [ "VideoMAEForPreTraining" ], "attention_probs_dropout_prob": 0.0, "decoder_hidden_size": 384, "decoder_intermediate_size": 1536, "decoder_num_attention_heads": 6, "decoder_num_hidden_layers": 4, "dtype": "float32", "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 64, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 128, "layer_norm_eps": 1e-12, "model_type": "videomae", "norm_pix_loss": true, "num_attention_heads": 4, "num_channels": 3, "num_frames": 16, "num_hidden_layers": 2, "patch_size": 16, "qv_bias": true, "transformers_version": "5.23.0.dev0", "tubelet_size": 2, "use_mean_pooling": false }