junnyu commited on
Commit
512e25c
1 Parent(s): 9b23ee3
Files changed (4) hide show
  1. config.json +22 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +16 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "gradient_checkpointing": false,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 24,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "type_vocab_size": 2,
20
+ "use_cache": true,
21
+ "vocab_size": 21128
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec794e64dbd602513dfd6c1a8f8e29354b0ce4a0aa51b7a21988ffbf2e84587
3
+ size 1302213171
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": true,
3
+ "do_basic_tokenize": true,
4
+ "never_split": null,
5
+ "unk_token": "[UNK]",
6
+ "sep_token": "[SEP]",
7
+ "pad_token": "[PAD]",
8
+ "cls_token": "[CLS]",
9
+ "mask_token": "[MASK]",
10
+ "tokenize_chinese_chars": true,
11
+ "strip_accents": null,
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_file": null,
14
+ "name_or_path": "junnyu/structbert-large-zh",
15
+ "tokenizer_class": "BertTokenizer"
16
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff