Shaltiel commited on
Commit
959e341
1 Parent(s): 6124495

Upload 6 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ vocab.txt filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForJointParsing"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "do_lex": true,
8
+ "do_morph": true,
9
+ "do_ner": true,
10
+ "do_prefix": true,
11
+ "do_syntax": true,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "B-ANG",
18
+ "1": "B-DUC",
19
+ "2": "B-EVE",
20
+ "3": "B-FAC",
21
+ "4": "B-GPE",
22
+ "5": "B-LOC",
23
+ "6": "B-ORG",
24
+ "7": "B-PER",
25
+ "8": "B-WOA",
26
+ "9": "B-INFORMAL",
27
+ "10": "B-MISC",
28
+ "11": "B-TIMEX",
29
+ "12": "B-TTL",
30
+ "13": "I-DUC",
31
+ "14": "I-EVE",
32
+ "15": "I-FAC",
33
+ "16": "I-GPE",
34
+ "17": "I-LOC",
35
+ "18": "I-ORG",
36
+ "19": "I-PER",
37
+ "20": "I-WOA",
38
+ "21": "I-ANG",
39
+ "22": "I-INFORMAL",
40
+ "23": "I-MISC",
41
+ "24": "I-TIMEX",
42
+ "25": "I-TTL",
43
+ "26": "O"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 3072,
47
+ "label2id": {
48
+ "B-ANG": 0,
49
+ "B-DUC": 1,
50
+ "B-EVE": 2,
51
+ "B-FAC": 3,
52
+ "B-GPE": 4,
53
+ "B-INFORMAL": 9,
54
+ "B-LOC": 5,
55
+ "B-MISC": 10,
56
+ "B-ORG": 6,
57
+ "B-PER": 7,
58
+ "B-TIMEX": 11,
59
+ "B-TTL": 12,
60
+ "B-WOA": 8,
61
+ "I-ANG": 21,
62
+ "I-DUC": 13,
63
+ "I-EVE": 14,
64
+ "I-FAC": 15,
65
+ "I-GPE": 16,
66
+ "I-INFORMAL": 22,
67
+ "I-LOC": 17,
68
+ "I-MISC": 23,
69
+ "I-ORG": 18,
70
+ "I-PER": 19,
71
+ "I-TIMEX": 24,
72
+ "I-TTL": 25,
73
+ "I-WOA": 20,
74
+ "O": 26
75
+ },
76
+ "layer_norm_eps": 1e-12,
77
+ "max_position_embeddings": 512,
78
+ "model_type": "bert",
79
+ "newmodern": true,
80
+ "num_attention_heads": 12,
81
+ "num_hidden_layers": 12,
82
+ "pad_token_id": 0,
83
+ "position_embedding_type": "absolute",
84
+ "syntax_head_size": 128,
85
+ "torch_dtype": "float32",
86
+ "transformers_version": "4.36.2",
87
+ "type_vocab_size": 2,
88
+ "use_cache": true,
89
+ "vocab_size": 128000
90
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2653b37a8f6ca942d42e0674b94bea5da5e7541ba5b4d847af2c6425a31921
3
+ size 744080096
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
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": "[BLANK]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "clean_up_tokenization_spaces": true,
53
+ "cls_token": "[CLS]",
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "model_max_length": 512,
57
+ "pad_token": "[PAD]",
58
+ "sep_token": "[SEP]",
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "unk_token": "[UNK]"
63
+ }
vocab.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb90bfa35244d26f0065d1fcd0b5becc3da3d44d616a7e2aacaf6320b9fa2d0
3
+ size 1500244