sravn commited on
Commit
d3d1dc7
1 Parent(s): 0ea3c1d

Initial commit

Browse files
config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/drive/MyDrive/Colab Notebooks/e2e-qg-bert",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "bert-base-uncased",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "BertForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "eos_token_id": null,
21
+ "finetuning_task": null,
22
+ "gradient_checkpointing": false,
23
+ "hidden_act": "gelu",
24
+ "hidden_dropout_prob": 0.1,
25
+ "hidden_size": 768,
26
+ "id2label": {
27
+ "0": "LABEL_0",
28
+ "1": "LABEL_1"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "is_decoder": true,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "layer_norm_eps": 1e-12,
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "max_position_embeddings": 512,
42
+ "min_length": 0,
43
+ "model_type": "bert",
44
+ "no_repeat_ngram_size": 0,
45
+ "num_attention_heads": 12,
46
+ "num_beam_groups": 1,
47
+ "num_beams": 1,
48
+ "num_hidden_layers": 12,
49
+ "num_return_sequences": 1,
50
+ "output_attentions": false,
51
+ "output_hidden_states": false,
52
+ "output_scores": false,
53
+ "pad_token_id": 0,
54
+ "position_embedding_type": "absolute",
55
+ "prefix": null,
56
+ "pruned_heads": {},
57
+ "repetition_penalty": 1.0,
58
+ "return_dict": true,
59
+ "return_dict_in_generate": false,
60
+ "sep_token_id": null,
61
+ "task_specific_params": null,
62
+ "temperature": 1.0,
63
+ "tie_encoder_decoder": false,
64
+ "tie_word_embeddings": true,
65
+ "tokenizer_class": null,
66
+ "top_k": 50,
67
+ "top_p": 1.0,
68
+ "torchscript": false,
69
+ "transformers_version": "4.2.1",
70
+ "type_vocab_size": 2,
71
+ "use_bfloat16": false,
72
+ "use_cache": true,
73
+ "vocab_size": 30522,
74
+ "xla_device": null
75
+ },
76
+ "decoder_start_token_id": 101,
77
+ "early_stopping": true,
78
+ "encoder": {
79
+ "_name_or_path": "bert-base-uncased",
80
+ "add_cross_attention": false,
81
+ "architectures": [
82
+ "BertForMaskedLM"
83
+ ],
84
+ "attention_probs_dropout_prob": 0.1,
85
+ "bad_words_ids": null,
86
+ "bos_token_id": null,
87
+ "chunk_size_feed_forward": 0,
88
+ "decoder_start_token_id": null,
89
+ "diversity_penalty": 0.0,
90
+ "do_sample": false,
91
+ "early_stopping": false,
92
+ "eos_token_id": null,
93
+ "finetuning_task": null,
94
+ "gradient_checkpointing": false,
95
+ "hidden_act": "gelu",
96
+ "hidden_dropout_prob": 0.1,
97
+ "hidden_size": 768,
98
+ "id2label": {
99
+ "0": "LABEL_0",
100
+ "1": "LABEL_1"
101
+ },
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-12,
111
+ "length_penalty": 1.0,
112
+ "max_length": 20,
113
+ "max_position_embeddings": 512,
114
+ "min_length": 0,
115
+ "model_type": "bert",
116
+ "no_repeat_ngram_size": 0,
117
+ "num_attention_heads": 12,
118
+ "num_beam_groups": 1,
119
+ "num_beams": 1,
120
+ "num_hidden_layers": 12,
121
+ "num_return_sequences": 1,
122
+ "output_attentions": false,
123
+ "output_hidden_states": false,
124
+ "output_scores": false,
125
+ "pad_token_id": 0,
126
+ "position_embedding_type": "absolute",
127
+ "prefix": null,
128
+ "pruned_heads": {},
129
+ "repetition_penalty": 1.0,
130
+ "return_dict": true,
131
+ "return_dict_in_generate": false,
132
+ "sep_token_id": null,
133
+ "task_specific_params": null,
134
+ "temperature": 1.0,
135
+ "tie_encoder_decoder": false,
136
+ "tie_word_embeddings": true,
137
+ "tokenizer_class": null,
138
+ "top_k": 50,
139
+ "top_p": 1.0,
140
+ "torchscript": false,
141
+ "transformers_version": "4.2.1",
142
+ "type_vocab_size": 2,
143
+ "use_bfloat16": false,
144
+ "use_cache": true,
145
+ "vocab_size": 30522,
146
+ "xla_device": null
147
+ },
148
+ "eos_token_id": 102,
149
+ "is_encoder_decoder": true,
150
+ "length_penalty": 0.25,
151
+ "max_length": 30,
152
+ "model_type": "encoder-decoder",
153
+ "no_repeat_ngram_size": 2,
154
+ "num_beams": 5,
155
+ "pad_token_id": 0,
156
+ "temperature": 0.95,
157
+ "vocab_size": 30522
158
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec32b446c5409bb142134043234dc1e7a64ead8915674ffd2fdf5447681cc200
3
+ size 989671659
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_special_tokens": true, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff