Token Classification
GLiNER
PyTorch
multilingual
Ihor commited on
Commit
e9c4d5c
1 Parent(s): e0bec71

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<<ENT>>": 128001,
3
+ "<<SEP>>": 128002,
4
+ "[MASK]": 128000
5
+ }
gliner_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": 128001,
3
+ "dropout": 0.4,
4
+ "encoder_config": null,
5
+ "ent_token": "<<ENT>>",
6
+ "fine_tune": true,
7
+ "has_rnn": true,
8
+ "hidden_size": 768,
9
+ "label_smoothing": 0.0,
10
+ "loss_alpha": 0.8,
11
+ "loss_gamma": 0,
12
+ "loss_reduction": "sum",
13
+ "max_len": 384,
14
+ "max_neg_type_ratio": 1,
15
+ "max_types": 30,
16
+ "max_width": 12,
17
+ "model_name": "microsoft/deberta-v3-base",
18
+ "model_type": "gliner",
19
+ "name": "span level gliner",
20
+ "random_drop": true,
21
+ "sep_token": "<<SEP>>",
22
+ "shuffle_types": true,
23
+ "span_mode": "markerV0",
24
+ "subtoken_pooling": "first",
25
+ "transformers_version": "4.40.2",
26
+ "vocab_size": 128003,
27
+ "words_splitter_type": "whitespace"
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bbe99f4e6b3bb32977697c85891d671223f04d4f73f258f31f3b2787c151a0
3
+ size 834285094
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[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": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128001": {
44
+ "content": "<<ENT>>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "128002": {
52
+ "content": "<<SEP>>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ }
59
+ },
60
+ "bos_token": "[CLS]",
61
+ "clean_up_tokenization_spaces": true,
62
+ "cls_token": "[CLS]",
63
+ "do_lower_case": false,
64
+ "eos_token": "[SEP]",
65
+ "mask_token": "[MASK]",
66
+ "model_max_length": 1000000000000000019884624838656,
67
+ "pad_token": "[PAD]",
68
+ "sep_token": "[SEP]",
69
+ "sp_model_kwargs": {},
70
+ "split_by_punct": false,
71
+ "tokenizer_class": "DebertaV2Tokenizer",
72
+ "unk_token": "[UNK]",
73
+ "vocab_type": "spm"
74
+ }