Hugging Face's logo

globalise
/
globalise_NER_token_classification

Token Classification
Safetensors
Dutch
roberta
Model card Files
xet
Community
sarnoult commited on
Commit
03d27f5
·
verified ·
1 Parent(s): dce9b77

Upload weights

Browse files
Files changed (7) hide show
  1. config.json +92 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +58 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-LOC_NAME",
15
+ "2": "I-LOC_NAME",
16
+ "3": "B-LOC_ADJ",
17
+ "4": "I-LOC_ADJ",
18
+ "5": "B-ETH_REL",
19
+ "6": "I-ETH_REL",
20
+ "7": "B-PER_NAME",
21
+ "8": "I-PER_NAME",
22
+ "9": "B-PRF",
23
+ "10": "I-PRF",
24
+ "11": "B-STATUS",
25
+ "12": "I-STATUS",
26
+ "13": "B-PER_ATTR",
27
+ "14": "I-PER_ATTR",
28
+ "15": "B-SHIP",
29
+ "16": "I-SHIP",
30
+ "17": "B-SHIP_TYPE",
31
+ "18": "I-SHIP_TYPE",
32
+ "19": "B-CMTY_NAME",
33
+ "20": "I-CMTY_NAME",
34
+ "21": "B-CMTY_QUAL",
35
+ "22": "I-CMTY_QUAL",
36
+ "23": "B-CMTY_QUANT",
37
+ "24": "I-CMTY_QUANT",
38
+ "25": "B-DATE",
39
+ "26": "I-DATE",
40
+ "27": "B-DOC",
41
+ "28": "I-DOC",
42
+ "29": "B-ORG",
43
+ "30": "I-ORG"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 3072,
47
+ "label2id": {
48
+ "O": 0,
49
+ "B-LOC_NAME": 1,
50
+ "I-LOC_NAME": 2,
51
+ "B-LOC_ADJ": 3,
52
+ "I-LOC_ADJ": 4,
53
+ "B-ETH_REL": 5,
54
+ "I-ETH_REL": 6,
55
+ "B-PER_NAME": 7,
56
+ "I-PER_NAME": 8,
57
+ "B-PRF": 9,
58
+ "I-PRF": 10,
59
+ "B-STATUS": 11,
60
+ "I-STATUS": 12,
61
+ "B-PER_ATTR": 13,
62
+ "I-PER_ATTR": 14,
63
+ "B-SHIP": 15,
64
+ "I-SHIP": 16,
65
+ "B-SHIP_TYPE": 17,
66
+ "I-SHIP_TYPE": 18,
67
+ "B-CMTY_NAME": 19,
68
+ "I-CMTY_NAME": 20,
69
+ "B-CMTY_QUAL": 21,
70
+ "I-CMTY_QUAL": 22,
71
+ "B-CMTY_QUANT": 23,
72
+ "I-CMTY_QUANT": 24,
73
+ "B-DATE": 25,
74
+ "I-DATE": 26,
75
+ "B-DOC": 27,
76
+ "I-DOC": 28,
77
+ "B-ORG": 29,
78
+ "I-ORG": 30
79
+ },
80
+ "layer_norm_eps": 1e-12,
81
+ "max_position_embeddings": 514,
82
+ "model_type": "roberta",
83
+ "num_attention_heads": 12,
84
+ "num_hidden_layers": 12,
85
+ "pad_token_id": 1,
86
+ "position_embedding_type": "absolute",
87
+ "torch_dtype": "float32",
88
+ "transformers_version": "4.55.4",
89
+ "type_vocab_size": 1,
90
+ "use_cache": true,
91
+ "vocab_size": 52000
92
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885b80166aaf3a4eccbcfb6bf3ba129b8e31ab68da989b4cf12e6ed61a4221f5
3
+ size 501669372
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff