system
Update config.json b47941a
1
{
2
  "architectures": [
3
    "EncoderDecoderModel"
4
  ],
5
  "decoder": {
6
    "add_cross_attention": true,
7
    "architectures": [
8
      "BertForMaskedLM"
9
    ],
10
    "attention_probs_dropout_prob": 0.1,
11
    "bad_words_ids": null,
12
    "bos_token_id": null,
13
    "decoder_start_token_id": null,
14
    "do_sample": false,
15
    "early_stopping": false,
16
    "eos_token_id": null,
17
    "finetuning_task": null,
18
    "hidden_act": "gelu",
19
    "hidden_dropout_prob": 0.1,
20
    "hidden_size": 768,
21
    "id2label": {
22
      "0": "LABEL_0",
23
      "1": "LABEL_1"
24
    },
25
    "initializer_range": 0.02,
26
    "intermediate_size": 3072,
27
    "is_decoder": true,
28
    "is_encoder_decoder": false,
29
    "label2id": {
30
      "LABEL_0": 0,
31
      "LABEL_1": 1
32
    },
33
    "layer_norm_eps": 1e-12,
34
    "length_penalty": 1.0,
35
    "max_length": 20,
36
    "max_position_embeddings": 512,
37
    "min_length": 0,
38
    "model_type": "bert",
39
    "no_repeat_ngram_size": 0,
40
    "num_attention_heads": 12,
41
    "num_beams": 1,
42
    "num_hidden_layers": 12,
43
    "num_return_sequences": 1,
44
    "output_attentions": false,
45
    "output_hidden_states": false,
46
    "pad_token_id": 0,
47
    "prefix": null,
48
    "pruned_heads": {},
49
    "repetition_penalty": 1.0,
50
    "task_specific_params": null,
51
    "temperature": 1.0,
52
    "top_k": 50,
53
    "top_p": 1.0,
54
    "torchscript": false,
55
    "type_vocab_size": 2,
56
    "use_bfloat16": false,
57
    "use_cache": true,
58
    "vocab_size": 28996,
59
    "xla_device": null
60
  },
61
  "encoder": {
62
    "architectures": [
63
      "BertForMaskedLM"
64
    ],
65
    "attention_probs_dropout_prob": 0.1,
66
    "bad_words_ids": null,
67
    "bos_token_id": null,
68
    "decoder_start_token_id": null,
69
    "do_sample": false,
70
    "early_stopping": false,
71
    "eos_token_id": null,
72
    "finetuning_task": null,
73
    "hidden_act": "gelu",
74
    "hidden_dropout_prob": 0.1,
75
    "hidden_size": 768,
76
    "id2label": {
77
      "0": "LABEL_0",
78
      "1": "LABEL_1"
79
    },
80
    "initializer_range": 0.02,
81
    "intermediate_size": 3072,
82
    "is_decoder": false,
83
    "is_encoder_decoder": false,
84
    "label2id": {
85
      "LABEL_0": 0,
86
      "LABEL_1": 1
87
    },
88
    "layer_norm_eps": 1e-12,
89
    "length_penalty": 1.0,
90
    "max_length": 20,
91
    "max_position_embeddings": 512,
92
    "min_length": 0,
93
    "model_type": "bert",
94
    "no_repeat_ngram_size": 0,
95
    "num_attention_heads": 12,
96
    "num_beams": 1,
97
    "num_hidden_layers": 12,
98
    "num_return_sequences": 1,
99
    "output_attentions": false,
100
    "output_hidden_states": false,
101
    "pad_token_id": 0,
102
    "prefix": null,
103
    "pruned_heads": {},
104
    "repetition_penalty": 1.0,
105
    "task_specific_params": null,
106
    "temperature": 1.0,
107
    "top_k": 50,
108
    "top_p": 1.0,
109
    "torchscript": false,
110
    "type_vocab_size": 2,
111
    "use_bfloat16": false,
112
    "use_cache": true,
113
    "vocab_size": 28996,
114
    "xla_device": null
115
  },
116
  "is_encoder_decoder": true,
117
  "model_type": "encoder-decoder"
118
}