mrm8488 commited on
Commit
c37d183
1 Parent(s): eb2a9eb

Initial commit from mrm8488

Browse files
config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "decoder_start_token_id": null,
16
+ "do_sample": false,
17
+ "early_stopping": false,
18
+ "eos_token_id": null,
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-12,
37
+ "length_penalty": 1.0,
38
+ "max_length": 20,
39
+ "max_position_embeddings": 512,
40
+ "min_length": 0,
41
+ "model_type": "bert",
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
+ "output_past": true,
50
+ "pad_token_id": 1,
51
+ "position_embedding_type": "absolute",
52
+ "prefix": null,
53
+ "pruned_heads": {},
54
+ "repetition_penalty": 1.0,
55
+ "return_dict": true,
56
+ "sep_token_id": null,
57
+ "task_specific_params": null,
58
+ "temperature": 1.0,
59
+ "tie_encoder_decoder": false,
60
+ "tie_word_embeddings": true,
61
+ "tokenizer_class": null,
62
+ "top_k": 50,
63
+ "top_p": 1.0,
64
+ "torchscript": false,
65
+ "type_vocab_size": 2,
66
+ "use_bfloat16": false,
67
+ "vocab_size": 31002,
68
+ "xla_device": null
69
+ },
70
+ "decoder_start_token_id": 4,
71
+ "early_stopping": true,
72
+ "encoder": {
73
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
74
+ "add_cross_attention": false,
75
+ "architectures": [
76
+ "BertForMaskedLM"
77
+ ],
78
+ "attention_probs_dropout_prob": 0.1,
79
+ "bad_words_ids": null,
80
+ "bos_token_id": null,
81
+ "chunk_size_feed_forward": 0,
82
+ "decoder_start_token_id": null,
83
+ "do_sample": false,
84
+ "early_stopping": false,
85
+ "eos_token_id": null,
86
+ "finetuning_task": null,
87
+ "gradient_checkpointing": false,
88
+ "hidden_act": "gelu",
89
+ "hidden_dropout_prob": 0.1,
90
+ "hidden_size": 768,
91
+ "id2label": {
92
+ "0": "LABEL_0",
93
+ "1": "LABEL_1"
94
+ },
95
+ "initializer_range": 0.02,
96
+ "intermediate_size": 3072,
97
+ "is_decoder": false,
98
+ "is_encoder_decoder": false,
99
+ "label2id": {
100
+ "LABEL_0": 0,
101
+ "LABEL_1": 1
102
+ },
103
+ "layer_norm_eps": 1e-12,
104
+ "length_penalty": 1.0,
105
+ "max_length": 20,
106
+ "max_position_embeddings": 512,
107
+ "min_length": 0,
108
+ "model_type": "bert",
109
+ "no_repeat_ngram_size": 0,
110
+ "num_attention_heads": 12,
111
+ "num_beams": 1,
112
+ "num_hidden_layers": 12,
113
+ "num_return_sequences": 1,
114
+ "output_attentions": false,
115
+ "output_hidden_states": false,
116
+ "output_past": true,
117
+ "pad_token_id": 1,
118
+ "position_embedding_type": "absolute",
119
+ "prefix": null,
120
+ "pruned_heads": {},
121
+ "repetition_penalty": 1.0,
122
+ "return_dict": true,
123
+ "sep_token_id": null,
124
+ "task_specific_params": null,
125
+ "temperature": 1.0,
126
+ "tie_encoder_decoder": false,
127
+ "tie_word_embeddings": true,
128
+ "tokenizer_class": null,
129
+ "top_k": 50,
130
+ "top_p": 1.0,
131
+ "torchscript": false,
132
+ "type_vocab_size": 2,
133
+ "use_bfloat16": false,
134
+ "vocab_size": 31002,
135
+ "xla_device": null
136
+ },
137
+ "eos_token_id": 5,
138
+ "is_encoder_decoder": true,
139
+ "length_penalty": 2.0,
140
+ "max_length": 128,
141
+ "min_length": 6,
142
+ "model_type": "encoder-decoder",
143
+ "no_repeat_ngram_size": 3,
144
+ "num_beams": 4,
145
+ "pad_token_id": 1,
146
+ "vocab_size": 31002
147
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485b4372e25e291ea262f2ada6687d5801efa4944b1a84780b0d09e7094b57e7
3
+ size 992637147
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": false, "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": "/root/.cache/huggingface/transformers/9848a00af462c42dfb4ec88ef438fbab5256330f7f6f50badc48d277f9367d49.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "dccuchile/bert-base-spanish-wwm-cased"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64fddf38f0ab99356c87d1272a6e3191906b78d5f946ebb17a4e2c61b5610f96
3
+ size 2095
vocab.txt ADDED
The diff for this file is too large to render. See raw diff