Hugging Face's logo

WikinewsSum
/
bert2bert-multi-en-wiki-news

Text2Text Generation Transformers PyTorch encoder-decoder Inference Endpoints
Model card Files Community
system HF staff commited on
Commit
d27c631
•
1 Parent(s): 81388e1

Update config.json

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