elmadany commited on
Commit
c8d7897
1 Parent(s): bf78689

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +25 -0
  2. special_tokens_map.json +7 -0
  3. tokenizer_config.json +15 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+
3
+ "attention_probs_dropout_prob": 0.1,
4
+ "directionality": "bidi",
5
+ "gradient_checkpointing": false,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 3072,
11
+ "layer_norm_eps": 1e-12,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "bert",
14
+ "num_attention_heads": 12,
15
+ "num_hidden_layers": 12,
16
+ "pad_token_id": 0,
17
+ "pooler_fc_size": 768,
18
+ "pooler_num_attention_heads": 12,
19
+ "pooler_num_fc_layers": 3,
20
+ "pooler_size_per_head": 128,
21
+ "pooler_type": "first_token_transform",
22
+ "position_embedding_type": "absolute",
23
+ "type_vocab_size": 2,
24
+ "vocab_size": 100000
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff