GreedySearch

 Graphs in : cluster, ONNX model architecture.

input_ids (heterogeneous) – I : object, the sequence used as a prompt for the generation. Shape is (batch_size, sequence_length).
max_length (heterogeneous) – I : object, the maximum length of the sequence to be generated. Shape is (1).
min_length (optional, heterogeneous) – I : object, the minimum length below which the score of eos_token_id is set to -Inf. Shape is (1).
repetition_penalty (optional, heterogeneous) – T : object, the parameter for repetition penalty. Default value 1.0 means no penalty. Accepts value > 0.0. Shape is (1).
vocab_mask (optional, heterogeneous) – I : object, mask of vocabulary. Words that masked with 0 are not allowed to be generated, and 1 is allowed. Shape is (vocab_size).
attention_mask (optional, heterogeneous) – I : object, custom attention mask. Shape is (batch_size, sequence_length).

 Parameters : cluster,

decoder : object, decoder subgraph to execute in a loop.
 decoder_start_token_id : integer, the id of the token that indicates decoding starts.
encoder : object, the subgraph for initialization of encoder and decoder. It will be called once before `decoder` subgraph.
 eos_token_id : integer, the id of the end-of-sequence token.
init_decoder : object, the subgraph for the first decoding run. It will be called once before `decoder` subgraph. This is relevant only for the GPT2 model. If this attribute is missing, the `decoder` subgraph will be used for all decoding runs.
 model_type : enum, model type: 0 for decoder only like GPT-2; 1 for encoder decoder like Bart.
 no_repeat_ngram_size : integer, no repeat ngrams size.
pad_token_id : integer, the id of the padding token.
vocab_size : integer, size of the vocabulary. If not provided, it will be inferred from the decoder subgraph’s output shape.
 training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
 lda coeff : float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value “1”.

 name (optional) : string, name of the node.