system HF staff commited on
Commit
aa245d5
1 Parent(s): 80ac6b2

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +129 -0
config.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "architectures": [
7
+ "BertForMaskedLM"
8
+ ],
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bad_words_ids": null,
11
+ "bos_token_id": null,
12
+ "decoder_start_token_id": null,
13
+ "directionality": "bidi",
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
+ "pooler_fc_size": 768,
48
+ "pooler_num_attention_heads": 12,
49
+ "pooler_num_fc_layers": 3,
50
+ "pooler_size_per_head": 128,
51
+ "pooler_type": "first_token_transform",
52
+ "prefix": null,
53
+ "pruned_heads": {},
54
+ "repetition_penalty": 1.0,
55
+ "task_specific_params": null,
56
+ "temperature": 1.0,
57
+ "top_k": 50,
58
+ "top_p": 1.0,
59
+ "torchscript": false,
60
+ "type_vocab_size": 2,
61
+ "use_bfloat16": false,
62
+ "use_cache": true,
63
+ "vocab_size": 119547,
64
+ "xla_device": null
65
+ },
66
+ "encoder": {
67
+ "architectures": [
68
+ "BertForMaskedLM"
69
+ ],
70
+ "attention_probs_dropout_prob": 0.1,
71
+ "bad_words_ids": null,
72
+ "bos_token_id": null,
73
+ "decoder_start_token_id": null,
74
+ "directionality": "bidi",
75
+ "do_sample": false,
76
+ "early_stopping": false,
77
+ "eos_token_id": null,
78
+ "finetuning_task": null,
79
+ "hidden_act": "gelu",
80
+ "hidden_dropout_prob": 0.1,
81
+ "hidden_size": 768,
82
+ "id2label": {
83
+ "0": "LABEL_0",
84
+ "1": "LABEL_1"
85
+ },
86
+ "initializer_range": 0.02,
87
+ "intermediate_size": 3072,
88
+ "is_decoder": false,
89
+ "is_encoder_decoder": false,
90
+ "label2id": {
91
+ "LABEL_0": 0,
92
+ "LABEL_1": 1
93
+ },
94
+ "layer_norm_eps": 1e-12,
95
+ "length_penalty": 1.0,
96
+ "max_length": 20,
97
+ "max_position_embeddings": 512,
98
+ "min_length": 0,
99
+ "model_type": "bert",
100
+ "no_repeat_ngram_size": 0,
101
+ "num_attention_heads": 12,
102
+ "num_beams": 1,
103
+ "num_hidden_layers": 12,
104
+ "num_return_sequences": 1,
105
+ "output_attentions": false,
106
+ "output_hidden_states": false,
107
+ "pad_token_id": 0,
108
+ "pooler_fc_size": 768,
109
+ "pooler_num_attention_heads": 12,
110
+ "pooler_num_fc_layers": 3,
111
+ "pooler_size_per_head": 128,
112
+ "pooler_type": "first_token_transform",
113
+ "prefix": null,
114
+ "pruned_heads": {},
115
+ "repetition_penalty": 1.0,
116
+ "task_specific_params": null,
117
+ "temperature": 1.0,
118
+ "top_k": 50,
119
+ "top_p": 1.0,
120
+ "torchscript": false,
121
+ "type_vocab_size": 2,
122
+ "use_bfloat16": false,
123
+ "use_cache": true,
124
+ "vocab_size": 119547,
125
+ "xla_device": null
126
+ },
127
+ "is_encoder_decoder": true,
128
+ "model_type": "encoder-decoder"
129
+ }