josecannete commited on
Commit
48e7313
1 Parent(s): f0b8c1b

updating all configs, adding both fast and legacy tokenizers, also adding tensorflow checkpoint for compatibility

Browse files
config.json CHANGED
@@ -1,8 +1,10 @@
1
  {
 
2
  "architectures": [
3
  "BertForMaskedLM"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
 
6
  "hidden_act": "gelu",
7
  "hidden_dropout_prob": 0.1,
8
  "hidden_size": 768,
@@ -15,6 +17,9 @@
15
  "num_hidden_layers": 12,
16
  "output_past": true,
17
  "pad_token_id": 1,
 
 
18
  "type_vocab_size": 2,
 
19
  "vocab_size": 31002
20
  }
 
1
  {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
3
  "architectures": [
4
  "BertForMaskedLM"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
 
17
  "num_hidden_layers": 12,
18
  "output_past": true,
19
  "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.4.2",
22
  "type_vocab_size": 2,
23
+ "use_cache": true,
24
  "vocab_size": 31002
25
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c4a4d8244976bb203235f59c670e099439b5bc9eb343b09d7fa049a0b68852a
3
- size 441944381
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e131a95091c777bbd45250fb647fec415010cb8cd1ad6e1d59babeb82a0be360
3
+ size 439621341
special_tokens_map.json CHANGED
@@ -1 +1,7 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "[UNK]",
3
+ "sep_token": "[SEP]",
4
+ "pad_token": "[PAD]",
5
+ "cls_token": "[CLS]",
6
+ "mask_token": "[MASK]"
7
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e063ca12f1e498b5ee57137365f3474ee10ef9d38bb26620cb022bddc0a026d
3
+ size 536635336
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,14 @@
1
- {"do_lower_case": false, "init_inputs": []}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": false,
3
+ "unk_token": "[UNK]",
4
+ "sep_token": "[SEP]",
5
+ "pad_token": "[PAD]",
6
+ "cls_token": "[CLS]",
7
+ "mask_token": "[MASK]",
8
+ "tokenize_chinese_chars": true,
9
+ "strip_accents": false,
10
+ "name_or_path": "./bert-base-spanish-wwm-cased",
11
+ "do_basic_tokenize": true,
12
+ "never_split": null,
13
+ "model_max_length": 512
14
+ }
vocab.txt CHANGED
@@ -939,42 +939,42 @@
939
  [unused932]
940
  [unused933]
941
  [unused934]
942
- [unused935]
943
- [unused936]
944
- [unused937]
945
- [unused938]
946
- [unused939]
947
- [unused940]
948
- [unused941]
949
- [unused942]
950
- [unused943]
951
- [unused944]
952
- [unused945]
953
- [unused946]
954
- [unused947]
955
- [unused948]
956
- [unused949]
957
- [unused950]
958
- [unused951]
959
- [unused952]
960
- [unused953]
961
- [unused954]
962
- [unused955]
963
- [unused956]
964
- [unused957]
965
- [unused958]
966
- [unused959]
967
- [unused960]
968
- [unused961]
969
- [unused962]
970
- [unused963]
971
- [unused964]
972
- [unused965]
973
- [unused966]
974
- [unused967]
975
- [unused968]
976
- [unused969]
977
- [unused970]
978
  ##7
979
  7
980
  ##w
 
939
  [unused932]
940
  [unused933]
941
  [unused934]
942
+ ##|
943
+ |
944
+ ##}
945
+ }
946
+ ##{
947
+ {
948
+ ##_
949
+ _
950
+ ##+
951
+ +
952
+ ##*
953
+ *
954
+ ##&
955
+ &
956
+ ##$
957
+ $
958
+ ##]
959
+ ]
960
+ ##[
961
+ [
962
+ ##=
963
+ =
964
+ ##>
965
+ >
966
+ ##<
967
+ <
968
+ ##@
969
+ @
970
+ ##\
971
+ \
972
+ ##/
973
+ /
974
+ ##%
975
+ %
976
+ ##;
977
+ ;
978
  ##7
979
  7
980
  ##w