FlavaModel(
  (text_model): FlavaTextModel(
    (embeddings): FlavaTextEmbeddings(
      (word_embeddings): Embedding(1124, 32, padding_idx=0)
      (position_embeddings): Embedding(512, 32)
      (token_type_embeddings): Embedding(2, 32)
      (LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
      (dropout): Dropout(p=0.0, inplace=False)
    )
    (encoder): FlavaEncoder(
      (layer): ModuleList(
        (0): FlavaLayerBetterTransformer()
        (1): FlavaLayerBetterTransformer()
        (2): FlavaLayerBetterTransformer()
        (3): FlavaLayerBetterTransformer()
        (4): FlavaLayerBetterTransformer()
      )
    )
    (layernorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
    (pooler): FlavaPooler(
      (dense): Linear(in_features=32, out_features=32, bias=True)
      (activation): Tanh()
    )
  )
  (image_model): FlavaImageModel(
    (embeddings): FlavaImageEmbeddings(
      (patch_embeddings): PatchEmbeddings(
        (projection): Conv2d(3, 32, kernel_size=(2, 2), stride=(2, 2))
      )
      (dropout): Dropout(p=0.0, inplace=False)
    )
    (encoder): FlavaEncoder(
      (layer): ModuleList(
        (0): FlavaLayerBetterTransformer()
        (1): FlavaLayerBetterTransformer()
        (2): FlavaLayerBetterTransformer()
        (3): FlavaLayerBetterTransformer()
        (4): FlavaLayerBetterTransformer()
      )
    )
    (layernorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
    (pooler): FlavaPooler(
      (dense): Linear(in_features=32, out_features=32, bias=True)
      (activation): Tanh()
    )
  )
  (multimodal_model): FlavaMultimodalModel(
    (encoder): FlavaEncoder(
      (layer): ModuleList(
        (0): FlavaLayerBetterTransformer()
        (1): FlavaLayerBetterTransformer()
        (2): FlavaLayerBetterTransformer()
        (3): FlavaLayerBetterTransformer()
        (4): FlavaLayerBetterTransformer()
      )
    )
    (layernorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
    (pooler): FlavaPooler(
      (dense): Linear(in_features=32, out_features=32, bias=True)
      (activation): Tanh()
    )
  )
  (image_projection): Linear(in_features=32, out_features=32, bias=True)
  (text_projection): Linear(in_features=32, out_features=32, bias=True)
  (image_to_mm_projection): Linear(in_features=32, out_features=32, bias=True)
  (text_to_mm_projection): Linear(in_features=32, out_features=32, bias=True)
)