Hugging Face's logo

kykim
/
bertshared-kor-base

Text2Text Generation Transformers PyTorch Korean encoder-decoder Inference Endpoints
Model card Files Community
2
kykim commited on
Commit
abc96ec
•
1 Parent(s): 3ec9930

model upload

Browse files
Files changed (4) hide show
  1. config.json +163 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +5 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "add_cross_attention": true,
7
+ "architectures": [
8
+ "BertForMaskedLM"
9
+ ],
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "bos_token_id": 2,
13
+ "chunk_size_feed_forward": 0,
14
+ "decoder_start_token_id": 2,
15
+ "directionality": "bidi",
16
+ "diversity_penalty": 0.0,
17
+ "do_sample": false,
18
+ "early_stopping": false,
19
+ "embedding_size": 768,
20
+ "eos_token_id": 3,
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
+ "pooler_fc_size": 768,
55
+ "pooler_num_attention_heads": 12,
56
+ "pooler_num_fc_layers": 3,
57
+ "pooler_size_per_head": 128,
58
+ "pooler_type": "first_token_transform",
59
+ "position_embedding_type": "absolute",
60
+ "prefix": null,
61
+ "pruned_heads": {},
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": 3,
66
+ "task_specific_params": null,
67
+ "temperature": 1.0,
68
+ "tie_encoder_decoder": false,
69
+ "tie_word_embeddings": true,
70
+ "tokenizer_class": null,
71
+ "top_k": 50,
72
+ "top_p": 1.0,
73
+ "torchscript": false,
74
+ "type_vocab_size": 2,
75
+ "use_bfloat16": false,
76
+ "use_cache": true,
77
+ "vocab_size": 42000,
78
+ "xla_device": null
79
+ },
80
+ "early_stopping": true,
81
+ "encoder": {
82
+ "add_cross_attention": false,
83
+ "architectures": [
84
+ "BertForMaskedLM"
85
+ ],
86
+ "attention_probs_dropout_prob": 0.1,
87
+ "bad_words_ids": null,
88
+ "bos_token_id": 2,
89
+ "chunk_size_feed_forward": 0,
90
+ "directionality": "bidi",
91
+ "diversity_penalty": 0.0,
92
+ "do_sample": false,
93
+ "early_stopping": false,
94
+ "embedding_size": 768,
95
+ "eos_token_id": 3,
96
+ "finetuning_task": null,
97
+ "gradient_checkpointing": false,
98
+ "hidden_act": "gelu",
99
+ "hidden_dropout_prob": 0.1,
100
+ "hidden_size": 768,
101
+ "id2label": {
102
+ "0": "LABEL_0",
103
+ "1": "LABEL_1"
104
+ },
105
+ "initializer_range": 0.02,
106
+ "intermediate_size": 3072,
107
+ "is_decoder": false,
108
+ "is_encoder_decoder": false,
109
+ "label2id": {
110
+ "LABEL_0": 0,
111
+ "LABEL_1": 1
112
+ },
113
+ "layer_norm_eps": 1e-12,
114
+ "length_penalty": 1.0,
115
+ "max_length": 20,
116
+ "max_position_embeddings": 512,
117
+ "min_length": 0,
118
+ "model_type": "bert",
119
+ "no_repeat_ngram_size": 0,
120
+ "num_attention_heads": 12,
121
+ "num_beam_groups": 1,
122
+ "num_beams": 1,
123
+ "num_hidden_layers": 12,
124
+ "num_return_sequences": 1,
125
+ "output_attentions": false,
126
+ "output_hidden_states": false,
127
+ "output_scores": false,
128
+ "pad_token_id": 0,
129
+ "pooler_fc_size": 768,
130
+ "pooler_num_attention_heads": 12,
131
+ "pooler_num_fc_layers": 3,
132
+ "pooler_size_per_head": 128,
133
+ "pooler_type": "first_token_transform",
134
+ "position_embedding_type": "absolute",
135
+ "prefix": null,
136
+ "pruned_heads": {},
137
+ "repetition_penalty": 1.0,
138
+ "return_dict": true,
139
+ "return_dict_in_generate": false,
140
+ "sep_token_id": 3,
141
+ "task_specific_params": null,
142
+ "temperature": 1.0,
143
+ "tie_encoder_decoder": false,
144
+ "tie_word_embeddings": true,
145
+ "tokenizer_class": null,
146
+ "top_k": 50,
147
+ "top_p": 1.0,
148
+ "torchscript": false,
149
+ "type_vocab_size": 2,
150
+ "use_bfloat16": false,
151
+ "use_cache": true,
152
+ "vocab_size": 42000,
153
+ "xla_device": null
154
+ },
155
+ "is_encoder_decoder": true,
156
+ "length_penalty": 1.5,
157
+ "min_length": 30,
158
+ "model_type": "encoder-decoder",
159
+ "no_repeat_ngram_size": 2,
160
+ "num_beams": 4,
161
+ "tie_encoder_decoder": true,
162
+ "vocab_size": 42000
163
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec07a9fe8f41b791fc48d82d1692da23b33a1db433b2780dc90b309c6fadbd40
3
+ size 589387271
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
1
+ {
2
+ "do_lower_case": true,
3
+ "strip_accents": false,
4
+ "model_max_length": 512
5
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff