Hugging Face's logo

wjc123
/
dobule_klue

Text2Text Generation
Transformers
PyTorch
encoder-decoder
Inference Endpoints
Model card Files Community
wjc123 commited on
Commit
0e54ae0
•
1 Parent(s): 46678d2

dobule klue model

Browse files
Files changed (2) hide show
  1. config.json +154 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "my-model",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "klue/bert-base",
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
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "finetuning_task": null,
23
+ "forced_bos_token_id": null,
24
+ "forced_eos_token_id": null,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 512,
45
+ "min_length": 0,
46
+ "model_type": "bert",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 12,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 0,
57
+ "position_embedding_type": "absolute",
58
+ "prefix": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "return_dict_in_generate": false,
64
+ "sep_token_id": null,
65
+ "task_specific_params": null,
66
+ "temperature": 1.0,
67
+ "tie_encoder_decoder": false,
68
+ "tie_word_embeddings": true,
69
+ "tokenizer_class": null,
70
+ "top_k": 50,
71
+ "top_p": 1.0,
72
+ "torchscript": false,
73
+ "transformers_version": "4.5.0",
74
+ "type_vocab_size": 2,
75
+ "use_bfloat16": false,
76
+ "use_cache": true,
77
+ "vocab_size": 32000
78
+ },
79
+ "encoder": {
80
+ "_name_or_path": "klue/bert-base",
81
+ "add_cross_attention": false,
82
+ "architectures": [
83
+ "BertForMaskedLM"
84
+ ],
85
+ "attention_probs_dropout_prob": 0.1,
86
+ "bad_words_ids": null,
87
+ "bos_token_id": null,
88
+ "chunk_size_feed_forward": 0,
89
+ "decoder_start_token_id": null,
90
+ "diversity_penalty": 0.0,
91
+ "do_sample": false,
92
+ "early_stopping": false,
93
+ "encoder_no_repeat_ngram_size": 0,
94
+ "eos_token_id": null,
95
+ "finetuning_task": null,
96
+ "forced_bos_token_id": null,
97
+ "forced_eos_token_id": null,
98
+ "gradient_checkpointing": false,
99
+ "hidden_act": "gelu",
100
+ "hidden_dropout_prob": 0.1,
101
+ "hidden_size": 768,
102
+ "id2label": {
103
+ "0": "LABEL_0",
104
+ "1": "LABEL_1"
105
+ },
106
+ "initializer_range": 0.02,
107
+ "intermediate_size": 3072,
108
+ "is_decoder": false,
109
+ "is_encoder_decoder": false,
110
+ "label2id": {
111
+ "LABEL_0": 0,
112
+ "LABEL_1": 1
113
+ },
114
+ "layer_norm_eps": 1e-12,
115
+ "length_penalty": 1.0,
116
+ "max_length": 20,
117
+ "max_position_embeddings": 512,
118
+ "min_length": 0,
119
+ "model_type": "bert",
120
+ "no_repeat_ngram_size": 0,
121
+ "num_attention_heads": 12,
122
+ "num_beam_groups": 1,
123
+ "num_beams": 1,
124
+ "num_hidden_layers": 12,
125
+ "num_return_sequences": 1,
126
+ "output_attentions": false,
127
+ "output_hidden_states": false,
128
+ "output_scores": false,
129
+ "pad_token_id": 0,
130
+ "position_embedding_type": "absolute",
131
+ "prefix": null,
132
+ "pruned_heads": {},
133
+ "remove_invalid_values": false,
134
+ "repetition_penalty": 1.0,
135
+ "return_dict": true,
136
+ "return_dict_in_generate": false,
137
+ "sep_token_id": null,
138
+ "task_specific_params": null,
139
+ "temperature": 1.0,
140
+ "tie_encoder_decoder": false,
141
+ "tie_word_embeddings": true,
142
+ "tokenizer_class": null,
143
+ "top_k": 50,
144
+ "top_p": 1.0,
145
+ "torchscript": false,
146
+ "transformers_version": "4.5.0",
147
+ "type_vocab_size": 2,
148
+ "use_bfloat16": false,
149
+ "use_cache": true,
150
+ "vocab_size": 32000
151
+ },
152
+ "is_encoder_decoder": true,
153
+ "model_type": "encoder-decoder"
154
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ff555ee226b642b402a7236f17f67ec77009753f3238bdcfa5b95c7a09497f
3
+ size 998758443