system
Update config.json 6082472
1
{
2
  "architectures": [
3
    "EncoderDecoderModel"
4
  ],
5
  "bos_token_id": 2,
6
  "decoder": {
7
    "add_cross_attention": true,
8
    "architectures": [
9
      "BertGenerationEncoder"
10
    ],
11
    "attention_probs_dropout_prob": 0.1,
12
    "bad_words_ids": null,
13
    "bos_token_id": null,
14
    "chunk_size_feed_forward": 0,
15
    "decoder_start_token_id": null,
16
    "directionality": "bidi",
17
    "do_sample": false,
18
    "early_stopping": false,
19
    "eos_token_id": null,
20
    "finetuning_task": null,
21
    "gradient_checkpointing": false,
22
    "hidden_act": "gelu",
23
    "hidden_dropout_prob": 0.1,
24
    "hidden_size": 1024,
25
    "id2label": {
26
      "0": "LABEL_0",
27
      "1": "LABEL_1"
28
    },
29
    "initializer_range": 0.02,
30
    "intermediate_size": 4096,
31
    "is_decoder": true,
32
    "is_encoder_decoder": false,
33
    "label2id": {
34
      "LABEL_0": 0,
35
      "LABEL_1": 1
36
    },
37
    "layer_norm_eps": 1e-12,
38
    "length_penalty": 1.0,
39
    "max_length": 20,
40
    "max_position_embeddings": 512,
41
    "min_length": 0,
42
    "model_type": "bert-generation",
43
    "no_repeat_ngram_size": 0,
44
    "num_attention_heads": 16,
45
    "num_beams": 1,
46
    "num_hidden_layers": 24,
47
    "num_return_sequences": 1,
48
    "output_attentions": false,
49
    "output_hidden_states": false,
50
    "pad_token_id": 0,
51
    "prefix": null,
52
    "pruned_heads": {},
53
    "repetition_penalty": 1.0,
54
    "return_dict": false,
55
    "task_specific_params": null,
56
    "temperature": 1.0,
57
    "tie_encoder_decoder": false,
58
    "tie_word_embeddings": true,
59
    "top_k": 50,
60
    "top_p": 1.0,
61
    "torchscript": false,
62
    "use_bfloat16": false,
63
    "use_cache": true,
64
    "vocab_size": 50358,
65
    "xla_device": null
66
  },
67
  "decoder_start_token_id": 2,
68
  "encoder": {
69
    "add_cross_attention": false,
70
    "architectures": [
71
      "BertGenerationDecoder"
72
    ],
73
    "attention_probs_dropout_prob": 0.1,
74
    "bad_words_ids": null,
75
    "bos_token_id": null,
76
    "chunk_size_feed_forward": 0,
77
    "decoder_start_token_id": null,
78
    "directionality": "bidi",
79
    "do_sample": false,
80
    "early_stopping": false,
81
    "eos_token_id": null,
82
    "finetuning_task": null,
83
    "gradient_checkpointing": false,
84
    "hidden_act": "gelu",
85
    "hidden_dropout_prob": 0.1,
86
    "hidden_size": 1024,
87
    "id2label": {
88
      "0": "LABEL_0",
89
      "1": "LABEL_1"
90
    },
91
    "initializer_range": 0.02,
92
    "intermediate_size": 4096,
93
    "is_decoder": false,
94
    "is_encoder_decoder": false,
95
    "label2id": {
96
      "LABEL_0": 0,
97
      "LABEL_1": 1
98
    },
99
    "layer_norm_eps": 1e-12,
100
    "length_penalty": 1.0,
101
    "max_length": 20,
102
    "max_position_embeddings": 512,
103
    "min_length": 0,
104
    "model_type": "bert-generation",
105
    "no_repeat_ngram_size": 0,
106
    "num_attention_heads": 16,
107
    "num_beams": 1,
108
    "num_hidden_layers": 24,
109
    "num_return_sequences": 1,
110
    "output_attentions": false,
111
    "output_hidden_states": false,
112
    "pad_token_id": 0,
113
    "prefix": null,
114
    "pruned_heads": {},
115
    "repetition_penalty": 1.0,
116
    "return_dict": false,
117
    "task_specific_params": null,
118
    "temperature": 1.0,
119
    "tie_encoder_decoder": false,
120
    "tie_word_embeddings": true,
121
    "top_k": 50,
122
    "top_p": 1.0,
123
    "torchscript": false,
124
    "use_bfloat16": false,
125
    "use_cache": true,
126
    "vocab_size": 50358,
127
    "xla_device": null
128
  },
129
  "eos_token_id": 1,
130
  "is_encoder_decoder": true,
131
  "max_length": 128,
132
  "model_type": "encoder-decoder",
133
  "num_beams": 4,
134
  "pad_token_id": 0,
135
  "tie_encoder_decoder": true
136
}