mrm8488 commited on
Commit
cda01c1
1 Parent(s): cc3a58f

Initial commit from mrm8488

Browse files
config.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
7
+ "add_cross_attention": true,
8
+ "architectures": null,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bad_words_ids": null,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "decoder_start_token_id": null,
14
+ "diversity_penalty": 0.0,
15
+ "do_sample": false,
16
+ "early_stopping": false,
17
+ "eos_token_id": null,
18
+ "finetuning_task": null,
19
+ "gradient_checkpointing": false,
20
+ "hidden_act": "gelu",
21
+ "hidden_dropout_prob": 0.1,
22
+ "hidden_size": 256,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1024,
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-12,
36
+ "length_penalty": 1.0,
37
+ "max_length": 20,
38
+ "max_position_embeddings": 512,
39
+ "min_length": 0,
40
+ "model_type": "bert",
41
+ "no_repeat_ngram_size": 0,
42
+ "num_attention_heads": 4,
43
+ "num_beam_groups": 1,
44
+ "num_beams": 1,
45
+ "num_hidden_layers": 4,
46
+ "num_return_sequences": 1,
47
+ "output_attentions": false,
48
+ "output_hidden_states": false,
49
+ "pad_token_id": 0,
50
+ "position_embedding_type": "absolute",
51
+ "prefix": null,
52
+ "pruned_heads": {},
53
+ "repetition_penalty": 1.0,
54
+ "return_dict": true,
55
+ "sep_token_id": null,
56
+ "task_specific_params": null,
57
+ "temperature": 1.0,
58
+ "tie_encoder_decoder": false,
59
+ "tie_word_embeddings": true,
60
+ "tokenizer_class": null,
61
+ "top_k": 50,
62
+ "top_p": 1.0,
63
+ "torchscript": false,
64
+ "type_vocab_size": 2,
65
+ "use_bfloat16": false,
66
+ "vocab_size": 30522,
67
+ "xla_device": null
68
+ },
69
+ "decoder_start_token_id": 101,
70
+ "early_stopping": true,
71
+ "encoder": {
72
+ "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
73
+ "add_cross_attention": false,
74
+ "architectures": null,
75
+ "attention_probs_dropout_prob": 0.1,
76
+ "bad_words_ids": null,
77
+ "bos_token_id": null,
78
+ "chunk_size_feed_forward": 0,
79
+ "decoder_start_token_id": null,
80
+ "diversity_penalty": 0.0,
81
+ "do_sample": false,
82
+ "early_stopping": false,
83
+ "eos_token_id": null,
84
+ "finetuning_task": null,
85
+ "gradient_checkpointing": false,
86
+ "hidden_act": "gelu",
87
+ "hidden_dropout_prob": 0.1,
88
+ "hidden_size": 256,
89
+ "id2label": {
90
+ "0": "LABEL_0",
91
+ "1": "LABEL_1"
92
+ },
93
+ "initializer_range": 0.02,
94
+ "intermediate_size": 1024,
95
+ "is_decoder": false,
96
+ "is_encoder_decoder": false,
97
+ "label2id": {
98
+ "LABEL_0": 0,
99
+ "LABEL_1": 1
100
+ },
101
+ "layer_norm_eps": 1e-12,
102
+ "length_penalty": 1.0,
103
+ "max_length": 20,
104
+ "max_position_embeddings": 512,
105
+ "min_length": 0,
106
+ "model_type": "bert",
107
+ "no_repeat_ngram_size": 0,
108
+ "num_attention_heads": 4,
109
+ "num_beam_groups": 1,
110
+ "num_beams": 1,
111
+ "num_hidden_layers": 4,
112
+ "num_return_sequences": 1,
113
+ "output_attentions": false,
114
+ "output_hidden_states": false,
115
+ "pad_token_id": 0,
116
+ "position_embedding_type": "absolute",
117
+ "prefix": null,
118
+ "pruned_heads": {},
119
+ "repetition_penalty": 1.0,
120
+ "return_dict": true,
121
+ "sep_token_id": null,
122
+ "task_specific_params": null,
123
+ "temperature": 1.0,
124
+ "tie_encoder_decoder": false,
125
+ "tie_word_embeddings": true,
126
+ "tokenizer_class": null,
127
+ "top_k": 50,
128
+ "top_p": 1.0,
129
+ "torchscript": false,
130
+ "type_vocab_size": 2,
131
+ "use_bfloat16": false,
132
+ "vocab_size": 30522,
133
+ "xla_device": null
134
+ },
135
+ "eos_token_id": 102,
136
+ "is_encoder_decoder": true,
137
+ "length_penalty": 2.0,
138
+ "max_length": 128,
139
+ "min_length": 6,
140
+ "model_type": "encoder-decoder",
141
+ "no_repeat_ngram_size": 3,
142
+ "num_beams": 4,
143
+ "pad_token_id": 0,
144
+ "tie_encoder_decoder": true,
145
+ "vocab_size": 30522
146
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1979614d51294d81f43d4ae736c2e56624d35e576dd1e6f678fca5b2e3b6b2bc
3
+ size 49363207
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"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, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "google/bert_uncased_L-4_H-256_A-4"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d80d69b69f9726806151ddcb7cbae2a2d17dfb8d9751950b5e13b1e522d4068
3
+ size 2095
vocab.txt ADDED
The diff for this file is too large to render. See raw diff