|
{ |
|
"activation_dropout": 0.1, |
|
"activation_function": "gelu", |
|
"architectures": [ |
|
"XLMProphetNetForConditionalGeneration" |
|
], |
|
"attention_dropout": 0.1, |
|
"bos_token_id": 2, |
|
"decoder_ffn_dim": 4096, |
|
"decoder_layerdrop": 0.0, |
|
"decoder_start_token_id": 2, |
|
"disable_ngram_loss": false, |
|
"dropout": 0.1, |
|
"encoder_ffn_dim": 4096, |
|
"encoder_layerdrop": 0.0, |
|
"eos_token_id": 2, |
|
"eps": 0.0, |
|
"hidden_size": 1024, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1", |
|
"2": "LABEL_2" |
|
}, |
|
"init_std": 0.02, |
|
"is_encoder_decoder": true, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1, |
|
"LABEL_2": 2 |
|
}, |
|
"max_length": 512, |
|
"max_position_embeddings": 512, |
|
"model_type": "xlm-prophetnet", |
|
"ngram": 2, |
|
"num_buckets": 32, |
|
"num_decoder_attention_heads": 16, |
|
"num_decoder_layers": 12, |
|
"num_encoder_attention_heads": 16, |
|
"num_encoder_layers": 12, |
|
"output_past": false, |
|
"pad_token_id": 0, |
|
"prefix": " ", |
|
"relative_max_distance": 128, |
|
"task_specific_params": { |
|
"summarization": { |
|
"early_stopping": true, |
|
"length_penalty": 2.0, |
|
"no_repeat_ngram_size": 3, |
|
"num_beams": 4 |
|
} |
|
}, |
|
"vocab_size": 250012 |
|
} |