system HF staff commited on
Commit
93c01e6
1 Parent(s): 99144d5

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +147 -0
config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "add_cross_attention": true,
7
+ "architectures": [
8
+ "RobertaForMaskedLM"
9
+ ],
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "bos_token_id": 0,
13
+ "chunk_size_feed_forward": 0,
14
+ "decoder_start_token_id": null,
15
+ "do_sample": false,
16
+ "early_stopping": false,
17
+ "eos_token_id": 2,
18
+ "finetuning_task": null,
19
+ "gradient_checkpointing": false,
20
+ "hidden_act": "gelu",
21
+ "hidden_dropout_prob": 0.1,
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "is_decoder": true,
30
+ "is_encoder_decoder": false,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "length_penalty": 1.0,
37
+ "max_length": 20,
38
+ "max_position_embeddings": 514,
39
+ "min_length": 0,
40
+ "model_type": "roberta",
41
+ "no_repeat_ngram_size": 0,
42
+ "num_attention_heads": 12,
43
+ "num_beams": 1,
44
+ "num_hidden_layers": 12,
45
+ "num_return_sequences": 1,
46
+ "output_attentions": false,
47
+ "output_hidden_states": false,
48
+ "pad_token_id": 1,
49
+ "prefix": null,
50
+ "pruned_heads": {},
51
+ "repetition_penalty": 1.0,
52
+ "return_dict": false,
53
+ "task_specific_params": null,
54
+ "temperature": 1.0,
55
+ "tie_encoder_decoder": false,
56
+ "top_k": 50,
57
+ "top_p": 1.0,
58
+ "torchscript": false,
59
+ "type_vocab_size": 1,
60
+ "use_bfloat16": false,
61
+ "use_cache": true,
62
+ "vocab_size": 50265,
63
+ "xla_device": null
64
+ },
65
+ "decoder_start_token_id": 0,
66
+ "encoder": {
67
+ "add_cross_attention": false,
68
+ "architectures": null,
69
+ "attention_mode": "longformer",
70
+ "attention_probs_dropout_prob": 0.1,
71
+ "attention_window": [
72
+ 512,
73
+ 512,
74
+ 512,
75
+ 512,
76
+ 512,
77
+ 512,
78
+ 512,
79
+ 512,
80
+ 512,
81
+ 512,
82
+ 512,
83
+ 512
84
+ ],
85
+ "bad_words_ids": null,
86
+ "bos_token_id": 0,
87
+ "chunk_size_feed_forward": 0,
88
+ "decoder_start_token_id": null,
89
+ "do_sample": false,
90
+ "early_stopping": false,
91
+ "eos_token_id": 2,
92
+ "finetuning_task": null,
93
+ "gradient_checkpointing": false,
94
+ "hidden_act": "gelu",
95
+ "hidden_dropout_prob": 0.1,
96
+ "hidden_size": 768,
97
+ "id2label": {
98
+ "0": "LABEL_0",
99
+ "1": "LABEL_1"
100
+ },
101
+ "ignore_attention_mask": false,
102
+ "initializer_range": 0.02,
103
+ "intermediate_size": 3072,
104
+ "is_decoder": false,
105
+ "is_encoder_decoder": false,
106
+ "label2id": {
107
+ "LABEL_0": 0,
108
+ "LABEL_1": 1
109
+ },
110
+ "layer_norm_eps": 1e-05,
111
+ "length_penalty": 1.0,
112
+ "max_length": 20,
113
+ "max_position_embeddings": 4098,
114
+ "min_length": 0,
115
+ "model_type": "longformer",
116
+ "no_repeat_ngram_size": 0,
117
+ "num_attention_heads": 12,
118
+ "num_beams": 1,
119
+ "num_hidden_layers": 12,
120
+ "num_return_sequences": 1,
121
+ "output_attentions": false,
122
+ "output_hidden_states": false,
123
+ "pad_token_id": 1,
124
+ "prefix": null,
125
+ "pruned_heads": {},
126
+ "repetition_penalty": 1.0,
127
+ "return_dict": false,
128
+ "sep_token_id": 2,
129
+ "task_specific_params": null,
130
+ "temperature": 1.0,
131
+ "tie_encoder_decoder": false,
132
+ "top_k": 50,
133
+ "top_p": 1.0,
134
+ "torchscript": false,
135
+ "type_vocab_size": 1,
136
+ "use_bfloat16": false,
137
+ "use_cache": true,
138
+ "vocab_size": 50265,
139
+ "xla_device": null
140
+ },
141
+ "eos_token_id": 2,
142
+ "is_encoder_decoder": true,
143
+ "max_length": 142,
144
+ "min_length": 56,
145
+ "model_type": "encoder_decoder",
146
+ "no_repeat_ngram_size": 3
147
+ }