josecannete commited on
Commit
27c33d2
1 Parent(s): ebd4ed4

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-uncased",
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:a73faae202dd33ef1cd322959596d69a53d02674f9f82de9bea8f223ee0576d1
3
- size 441944381
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5480283d2ac26ac36df538fa5c12412b89ff176db693d00e71735200d9e0e99b
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 sha256:07e82361c425346a2d05b8f7ed638388e1f617416e2d9763224ff96ca0914e18
3
+ size 536635336
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,13 @@
1
- {"do_lower_case": true, "init_inputs": []}
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": true,
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
+ "do_basic_tokenize": true,
11
+ "never_split": null,
12
+ "model_max_length": 512
13
+ }
vocab.txt CHANGED
@@ -956,42 +956,42 @@
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
- [unused971]
979
- [unused972]
980
- [unused973]
981
- [unused974]
982
- [unused975]
983
- [unused976]
984
- [unused977]
985
- [unused978]
986
- [unused979]
987
- [unused980]
988
- [unused981]
989
- [unused982]
990
- [unused983]
991
- [unused984]
992
- [unused985]
993
- [unused986]
994
- [unused987]
995
  ##:
996
  :
997
  ##8
 
956
  [unused949]
957
  [unused950]
958
  [unused951]
959
+ ##|
960
+ |
961
+ ##}
962
+ }
963
+ ##{
964
+ {
965
+ ##_
966
+ _
967
+ ##+
968
+ +
969
+ ##*
970
+ *
971
+ ##&
972
+ &
973
+ ##$
974
+ $
975
+ ##]
976
+ ]
977
+ ##[
978
+ [
979
+ ##=
980
+ =
981
+ ##>
982
+ >
983
+ ##<
984
+ <
985
+ ##@
986
+ @
987
+ ##\
988
+ \
989
+ ##/
990
+ /
991
+ ##%
992
+ %
993
+ ##;
994
+ ;
995
  ##:
996
  :
997
  ##8