File size: 2,055 Bytes
805464a
90d7728
805464a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90d7728
805464a
 
90d7728
 
805464a
90d7728
805464a
 
90d7728
805464a
 
90d7728
 
805464a
90d7728
805464a
90d7728
805464a
90d7728
805464a
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
{
  "_name_or_path": "DarrenChensformer/mrebel-large-trim-zh",
  "_num_labels": 3,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "add_bias_logits": false,
  "add_final_layer_norm": true,
  "architectures": [
    "MBartForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "classif_dropout": 0.0,
  "classifier_dropout": 0.0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 0,
  "dropout": 0.1,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "forced_eos_token_id": 2,
  "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_length": 200,
  "max_position_embeddings": 1024,
  "model_type": "mbart",
  "normalize_before": true,
  "normalize_embedding": true,
  "num_beams": 5,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "scale_embedding": true,
  "static_position_embeddings": false,
  "tokenizer_class": "MBart50Tokenizer",
  "torch_dtype": "float32",
  "transformers_version": "4.34.1",
  "use_cache": true,
  "vocab_size": 60069,
  "vocabtrimmer": {
    "mining_config": {
      "dataset": "ikala/datahub-2023Q3",
      "dataset_column": "content",
      "dataset_name": "zh",
      "dataset_split": "train",
      "language": "zh",
      "min_frequency": 2,
      "target_vocab_size": 60000
    },
    "stats": {
      "compression_rate_embedding": 24.02077809901988,
      "compression_rate_full": 68.15140995576445,
      "parameter_size_embedding/raw": 256072704,
      "parameter_size_embedding/trimmed": 61510656,
      "parameter_size_full/raw": 610896896,
      "parameter_size_full/trimmed": 416334848,
      "vocab_size/raw": 250071,
      "vocab_size/trimmed": 60069
    }
  }
}