Hugging Face's logo

google
/
roberta2roberta_L-24_gigaword

Summarization
Transformers
PyTorch
English
encoder-decoder
text2text-generation
Inference Endpoints
Model card Files Community
1
system HF staff commited on
Commit
90ed968
•
1 Parent(s): cabbc97

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +140 -0
config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "add_cross_attention": true,
7
+ "architectures": [
8
+ "BertForSeqGenerationDecoder"
9
+ ],
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "bos_token_id": null,
13
+ "chunk_size_feed_forward": 0,
14
+ "decoder_start_token_id": null,
15
+ "directionality": "bidi",
16
+ "do_sample": false,
17
+ "early_stopping": false,
18
+ "eos_token_id": null,
19
+ "finetuning_task": null,
20
+ "gradient_checkpointing": false,
21
+ "hidden_act": "gelu",
22
+ "hidden_dropout_prob": 0.1,
23
+ "hidden_size": 1024,
24
+ "id2label": {
25
+ "0": "LABEL_0",
26
+ "1": "LABEL_1"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 4096,
30
+ "is_decoder": true,
31
+ "is_encoder_decoder": false,
32
+ "label2id": {
33
+ "LABEL_0": 0,
34
+ "LABEL_1": 1
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "length_penalty": 1.0,
38
+ "max_length": 20,
39
+ "max_position_embeddings": 512,
40
+ "min_length": 0,
41
+ "model_type": "bert-for-seq-generation",
42
+ "no_repeat_ngram_size": 0,
43
+ "num_attention_heads": 16,
44
+ "num_beams": 1,
45
+ "num_hidden_layers": 24,
46
+ "num_return_sequences": 1,
47
+ "output_attentions": false,
48
+ "output_hidden_states": false,
49
+ "pad_token_id": 0,
50
+ "pooler_fc_size": 768,
51
+ "pooler_num_attention_heads": 12,
52
+ "pooler_num_fc_layers": 3,
53
+ "pooler_size_per_head": 128,
54
+ "pooler_type": "first_token_transform",
55
+ "prefix": null,
56
+ "pruned_heads": {},
57
+ "repetition_penalty": 1.0,
58
+ "return_dict": false,
59
+ "task_specific_params": null,
60
+ "temperature": 1.0,
61
+ "tie_encoder_decoder": false,
62
+ "tie_word_embeddings": true,
63
+ "top_k": 50,
64
+ "top_p": 1.0,
65
+ "torchscript": false,
66
+ "use_bfloat16": false,
67
+ "use_cache": true,
68
+ "vocab_size": 50358,
69
+ "xla_device": null
70
+ },
71
+ "encoder": {
72
+ "add_cross_attention": false,
73
+ "architectures": [
74
+ "BertForSeqGenerationDecoder"
75
+ ],
76
+ "attention_probs_dropout_prob": 0.1,
77
+ "bad_words_ids": null,
78
+ "bos_token_id": null,
79
+ "chunk_size_feed_forward": 0,
80
+ "decoder_start_token_id": null,
81
+ "directionality": "bidi",
82
+ "do_sample": false,
83
+ "early_stopping": false,
84
+ "eos_token_id": null,
85
+ "finetuning_task": null,
86
+ "gradient_checkpointing": false,
87
+ "hidden_act": "gelu",
88
+ "hidden_dropout_prob": 0.1,
89
+ "hidden_size": 1024,
90
+ "id2label": {
91
+ "0": "LABEL_0",
92
+ "1": "LABEL_1"
93
+ },
94
+ "initializer_range": 0.02,
95
+ "intermediate_size": 4096,
96
+ "is_decoder": false,
97
+ "is_encoder_decoder": false,
98
+ "label2id": {
99
+ "LABEL_0": 0,
100
+ "LABEL_1": 1
101
+ },
102
+ "layer_norm_eps": 1e-12,
103
+ "length_penalty": 1.0,
104
+ "max_length": 20,
105
+ "max_position_embeddings": 512,
106
+ "min_length": 0,
107
+ "model_type": "bert-for-seq-generation",
108
+ "no_repeat_ngram_size": 0,
109
+ "num_attention_heads": 16,
110
+ "num_beams": 1,
111
+ "num_hidden_layers": 24,
112
+ "num_return_sequences": 1,
113
+ "output_attentions": false,
114
+ "output_hidden_states": false,
115
+ "pad_token_id": 0,
116
+ "pooler_fc_size": 768,
117
+ "pooler_num_attention_heads": 12,
118
+ "pooler_num_fc_layers": 3,
119
+ "pooler_size_per_head": 128,
120
+ "pooler_type": "first_token_transform",
121
+ "prefix": null,
122
+ "pruned_heads": {},
123
+ "repetition_penalty": 1.0,
124
+ "return_dict": false,
125
+ "task_specific_params": null,
126
+ "temperature": 1.0,
127
+ "tie_encoder_decoder": false,
128
+ "tie_word_embeddings": true,
129
+ "top_k": 50,
130
+ "top_p": 1.0,
131
+ "torchscript": false,
132
+ "use_bfloat16": false,
133
+ "use_cache": true,
134
+ "vocab_size": 50358,
135
+ "xla_device": null
136
+ },
137
+ "is_encoder_decoder": true,
138
+ "model_type": "encoder_decoder",
139
+ "tie_encoder_decoder": true
140
+ }