wjn1996 commited on
Commit
4ff0a4c
1 Parent(s): 4bcefd4

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +38 -0
  2. special_tokens_map.json +7 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +14 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "RoPE": true,
3
+ "_name_or_path": "/wjn/projects/information_extraction/HugIE/outputs/zh_instruction/chinese-macbert-large/chinese-macbert-large",
4
+ "architectures": [
5
+ "BertForEffiGlobalPointer"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "directionality": "bidi",
11
+ "ent_type_size": 1,
12
+ "eos_token_id": 2,
13
+ "finetuning_task": "laic",
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 1024,
17
+ "initializer_range": 0.02,
18
+ "inner_dim": 64,
19
+ "intermediate_size": 4096,
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 24,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "pooler_fc_size": 768,
28
+ "pooler_num_attention_heads": 12,
29
+ "pooler_num_fc_layers": 3,
30
+ "pooler_size_per_head": 128,
31
+ "pooler_type": "first_token_transform",
32
+ "position_embedding_type": "absolute",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.21.2",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 21128
38
+ }
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "name_or_path": "/wjn/projects/information_extraction/HugIE/outputs/zh_instruction/chinese-macbert-large/chinese-macbert-large",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "special_tokens_map_file": "/wjn/pre-trained-lm/chinese-macbert-large/special_tokens_map.json",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]",
13
+ "use_fast": true
14
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff