View Source Bumblebee.Text.ClipText (Bumblebee v0.6.0)
The CLIP model for text encoding.
Architectures
:base
- the base text model:for_embedding
- the base model with a single projection layer on top. The head returns a vector embedded in the joint text-image CLIP space
Inputs
"input_ids"
-{batch_size, sequence_length}
Indices of input sequence tokens in the vocabulary.
"attention_mask"
-{batch_size, sequence_length}
Mask indicating which tokens to attend to. This is used to ignore padding tokens, which are added when processing a batch of sequences with different length.
"position_ids"
-{batch_size, sequence_length}
Indices of positions of each input sequence tokens in the position embeddings.
Global layer options
:output_hidden_states
- whentrue
, the model output includes all hidden states:output_attentions
- whentrue
, the model output includes all attention weights
Configuration
:vocab_size
- the vocabulary size of the token embedding. This corresponds to the number of distinct tokens that can be represented in model input and output . Defaults to49408
:max_positions
- the vocabulary size of the position embedding. This corresponds to the maximum sequence length that this model can process. Typically this is set to a large value just in case, such as 512, 1024 or 2048 . Defaults to77
:hidden_size
- the dimensionality of hidden layers. Defaults to512
:num_blocks
- the number of Transformer blocks in the encoder. Defaults to12
:num_attention_heads
- the number of attention heads for each attention layer in the encoder. Defaults to8
:intermediate_size
- the dimensionality of the intermediate layer in the transformer feed-forward network (FFN) in the encoder. Defaults to2048
:projection_size
- the dimensionality of the projection layer. Defaults to512
:activation
- the activation function. Defaults to:gelu_approx_sigmoid
:attention_dropout_rate
- the dropout rate for attention weights. Defaults to0.0
:layer_norm_epsilon
- the epsilon used by the layer normalization layers. Defaults to1.0e-5
:num_labels
- the number of labels to use in the last layer for the classification task. Defaults to2
:id_to_label
- a map from class index to label. Defaults to%{}