system HF staff commited on
Commit
0f63114
1 Parent(s): 33f4a9f

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +144 -0
config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "roberta-base",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "RobertaForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "decoder_start_token_id": null,
16
+ "do_sample": false,
17
+ "early_stopping": false,
18
+ "eos_token_id": 2,
19
+ "finetuning_task": null,
20
+ "gradient_checkpointing": false,
21
+ "hidden_act": "gelu",
22
+ "hidden_dropout_prob": 0.1,
23
+ "hidden_size": 768,
24
+ "id2label": {
25
+ "0": "LABEL_0",
26
+ "1": "LABEL_1"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
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-05,
37
+ "length_penalty": 1.0,
38
+ "max_length": 20,
39
+ "max_position_embeddings": 514,
40
+ "min_length": 0,
41
+ "model_type": "roberta",
42
+ "no_repeat_ngram_size": 0,
43
+ "num_attention_heads": 12,
44
+ "num_beams": 1,
45
+ "num_hidden_layers": 12,
46
+ "num_return_sequences": 1,
47
+ "output_attentions": false,
48
+ "output_hidden_states": false,
49
+ "pad_token_id": 1,
50
+ "prefix": null,
51
+ "pruned_heads": {},
52
+ "repetition_penalty": 1.0,
53
+ "return_dict": false,
54
+ "sep_token_id": null,
55
+ "task_specific_params": null,
56
+ "temperature": 1.0,
57
+ "tie_encoder_decoder": false,
58
+ "tie_word_embeddings": true,
59
+ "tokenizer_class": null,
60
+ "top_k": 50,
61
+ "top_p": 1.0,
62
+ "torchscript": false,
63
+ "type_vocab_size": 1,
64
+ "use_bfloat16": false,
65
+ "use_cache": true,
66
+ "vocab_size": 50265,
67
+ "xla_device": null
68
+ },
69
+ "decoder_start_token_id": 0,
70
+ "early_stopping": true,
71
+ "encoder": {
72
+ "_name_or_path": "roberta-base",
73
+ "add_cross_attention": false,
74
+ "architectures": [
75
+ "RobertaForMaskedLM"
76
+ ],
77
+ "attention_probs_dropout_prob": 0.1,
78
+ "bad_words_ids": null,
79
+ "bos_token_id": 0,
80
+ "chunk_size_feed_forward": 0,
81
+ "decoder_start_token_id": null,
82
+ "do_sample": false,
83
+ "early_stopping": false,
84
+ "eos_token_id": 2,
85
+ "finetuning_task": null,
86
+ "gradient_checkpointing": false,
87
+ "hidden_act": "gelu",
88
+ "hidden_dropout_prob": 0.1,
89
+ "hidden_size": 768,
90
+ "id2label": {
91
+ "0": "LABEL_0",
92
+ "1": "LABEL_1"
93
+ },
94
+ "initializer_range": 0.02,
95
+ "intermediate_size": 3072,
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-05,
103
+ "length_penalty": 1.0,
104
+ "max_length": 20,
105
+ "max_position_embeddings": 514,
106
+ "min_length": 0,
107
+ "model_type": "roberta",
108
+ "no_repeat_ngram_size": 0,
109
+ "num_attention_heads": 12,
110
+ "num_beams": 1,
111
+ "num_hidden_layers": 12,
112
+ "num_return_sequences": 1,
113
+ "output_attentions": false,
114
+ "output_hidden_states": false,
115
+ "pad_token_id": 1,
116
+ "prefix": null,
117
+ "pruned_heads": {},
118
+ "repetition_penalty": 1.0,
119
+ "return_dict": false,
120
+ "sep_token_id": null,
121
+ "task_specific_params": null,
122
+ "temperature": 1.0,
123
+ "tie_encoder_decoder": false,
124
+ "tie_word_embeddings": true,
125
+ "tokenizer_class": null,
126
+ "top_k": 50,
127
+ "top_p": 1.0,
128
+ "torchscript": false,
129
+ "type_vocab_size": 1,
130
+ "use_bfloat16": false,
131
+ "use_cache": true,
132
+ "vocab_size": 50265,
133
+ "xla_device": null
134
+ },
135
+ "eos_token_id": 2,
136
+ "is_encoder_decoder": true,
137
+ "length_penalty": 2.0,
138
+ "max_length": 64,
139
+ "model_type": "encoder-decoder",
140
+ "no_repeat_ngram_size": 3,
141
+ "num_beams": 4,
142
+ "tie_encoder_decoder": true,
143
+ "vocab_size": 50265
144
+ }