|
{ |
|
"_name_or_path": "fnlp/cpt-base", |
|
"activation_dropout": 0.1, |
|
"activation_function": "gelu", |
|
"add_bias_logits": false, |
|
"add_final_layer_norm": false, |
|
"architectures": [ |
|
"CPTForConditionalGeneration" |
|
], |
|
"attention_dropout": 0.1, |
|
"bos_token_id": 101, |
|
"classif_dropout": 0.1, |
|
"classifier_dropout": 0.1, |
|
"d_model": 768, |
|
"decoder_attention_heads": 12, |
|
"decoder_ffn_dim": 3072, |
|
"decoder_layerdrop": 0.0, |
|
"decoder_layers": 2, |
|
"decoder_start_token_id": 102, |
|
"dropout": 0.1, |
|
"early_stopping": true, |
|
"efficient_methods": [], |
|
"encoder_attention_heads": 12, |
|
"encoder_ffn_dim": 3072, |
|
"encoder_layerdrop": 0.0, |
|
"encoder_layers": 12, |
|
"eos_token_id": 102, |
|
"forced_eos_token_id": 102, |
|
"gradient_checkpointing": false, |
|
"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_position_embeddings": 1024, |
|
"model_type": "bart", |
|
"no_repeat_ngram_size": 3, |
|
"normalize_before": false, |
|
"normalize_embedding": true, |
|
"num_beams": 4, |
|
"num_hidden_layers": 12, |
|
"pad_token_id": 0, |
|
"scale_embedding": false, |
|
"task_specific_params": { |
|
"summarization": { |
|
"length_penalty": 1.0, |
|
"max_length": 128, |
|
"min_length": 12, |
|
"num_beams": 4 |
|
}, |
|
"summarization_cnn": { |
|
"length_penalty": 2.0, |
|
"max_length": 142, |
|
"min_length": 56, |
|
"num_beams": 4 |
|
}, |
|
"summarization_xsum": { |
|
"length_penalty": 1.0, |
|
"max_length": 62, |
|
"min_length": 11, |
|
"num_beams": 6 |
|
} |
|
}, |
|
"tokenizer_class": "BertTokenizer", |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.26.0.dev0", |
|
"use_cache": true, |
|
"vocab_size": 51271 |
|
} |
|
|