Hugging Face's logo

hiroshi-matsuda-rit
/
bert-japanese-large-2k

PyTorch
bert
Model card Files Community
hiroshi-matsuda-rit commited on
Commit
b8666b9
•
1 Parent(s): f0ecd90

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +20 -0
  2. pytorch_model.bin +3 -0
  3. special_tokens_map.json +12 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +82 -0
config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "hidden_act": "gelu",
4
+ "hidden_dropout_prob": 0.1,
5
+ "hidden_size": 1024,
6
+ "initializer_range": 0.02,
7
+ "intermediate_size": 4096,
8
+ "layer_norm_eps": 1e-12,
9
+ "max_position_embeddings": 2048,
10
+ "model_type": "megatron-bert",
11
+ "num_attention_heads": 16,
12
+ "num_hidden_layers": 24,
13
+ "pad_token_id": 0,
14
+ "position_embedding_type": "absolute",
15
+ "tokenizer_type": "SentencePieceTokenizer",
16
+ "transformers_version": "4.45.0",
17
+ "type_vocab_size": 2,
18
+ "use_cache": true,
19
+ "vocab_size": 44544
20
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b03659f24473117bc6956a53d33b0fde5bee2e3ad0347f76f015482de6b048
3
+ size 1408796354
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<EOD>"
4
+ ],
5
+ "bos_token": "<s>",
6
+ "cls_token": "<CLS>",
7
+ "eos_token": "</s>",
8
+ "mask_token": "<MASK>",
9
+ "pad_token": "<PAD>",
10
+ "sep_token": "<SEP>",
11
+ "unk_token": "<unk>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<PAD>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<CLS>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<SEP>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<MASK>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<EOD>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<s>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "</s>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<EOD>"
70
+ ],
71
+ "bos_token": "<s>",
72
+ "clean_up_tokenization_spaces": false,
73
+ "cls_token": "<CLS>",
74
+ "eod_token": "<EOD>",
75
+ "eos_token": "</s>",
76
+ "mask_token": "<MASK>",
77
+ "model_max_length": 2048,
78
+ "pad_token": "<PAD>",
79
+ "sep_token": "<SEP>",
80
+ "tokenizer_class": "PreTrainedTokenizerFast",
81
+ "unk_token": "<unk>"
82
+ }