Hugging Face's logo

emanjavacas
/
robbert-2023-dutch-large-adapted-fine.ner

Safetensors
roberta
Model card Files Community
emanjavacas commited on
Commit
08abb2a
·
verified ·
1 Parent(s): 4eca398

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +87 -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 +57 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "robbert-2023-dutch-large-adapted",
3
+ "additional_special_tokens_ids": [],
4
+ "architectures": [
5
+ "RobertaForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "cls_token_id": 0,
11
+ "eos_token_id": 1,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "id2label": {
16
+ "0": "B-E_DATE",
17
+ "1": "B-E_LOC",
18
+ "2": "B-E_TIME",
19
+ "3": "B-P_AGE",
20
+ "4": "B-P_BIRTHDATE",
21
+ "5": "B-P_BIRTHPLACE",
22
+ "6": "B-P_FIRSTNAME",
23
+ "7": "B-P_LASTNAME",
24
+ "8": "B-P_MARITALSTATUS",
25
+ "9": "B-P_PROF",
26
+ "10": "B-P_RES",
27
+ "11": "B-P_TITLE",
28
+ "12": "I-E_DATE",
29
+ "13": "I-E_LOC",
30
+ "14": "I-E_TIME",
31
+ "15": "I-P_AGE",
32
+ "16": "I-P_BIRTHDATE",
33
+ "17": "I-P_BIRTHPLACE",
34
+ "18": "I-P_FIRSTNAME",
35
+ "19": "I-P_LASTNAME",
36
+ "20": "I-P_MARITALSTATUS",
37
+ "21": "I-P_PROF",
38
+ "22": "I-P_RES",
39
+ "23": "I-P_TITLE",
40
+ "24": "O"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 4096,
44
+ "label2id": {
45
+ "B-E_DATE": 0,
46
+ "B-E_LOC": 1,
47
+ "B-E_TIME": 2,
48
+ "B-P_AGE": 3,
49
+ "B-P_BIRTHDATE": 4,
50
+ "B-P_BIRTHPLACE": 5,
51
+ "B-P_FIRSTNAME": 6,
52
+ "B-P_LASTNAME": 7,
53
+ "B-P_MARITALSTATUS": 8,
54
+ "B-P_PROF": 9,
55
+ "B-P_RES": 10,
56
+ "B-P_TITLE": 11,
57
+ "I-E_DATE": 12,
58
+ "I-E_LOC": 13,
59
+ "I-E_TIME": 14,
60
+ "I-P_AGE": 15,
61
+ "I-P_BIRTHDATE": 16,
62
+ "I-P_BIRTHPLACE": 17,
63
+ "I-P_FIRSTNAME": 18,
64
+ "I-P_LASTNAME": 19,
65
+ "I-P_MARITALSTATUS": 20,
66
+ "I-P_PROF": 21,
67
+ "I-P_RES": 22,
68
+ "I-P_TITLE": 23,
69
+ "O": 24
70
+ },
71
+ "layer_norm_eps": 1e-05,
72
+ "mask_token_id": 4,
73
+ "max_position_embeddings": 514,
74
+ "model_type": "roberta",
75
+ "num_attention_heads": 16,
76
+ "num_hidden_layers": 24,
77
+ "pad_token_id": 1,
78
+ "position_embedding_type": "absolute",
79
+ "sep_token_id": 3,
80
+ "tokenizer_class": "RobertaTokenizerFast",
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.37.2",
83
+ "type_vocab_size": 1,
84
+ "unk_token_id": 2,
85
+ "use_cache": true,
86
+ "vocab_size": 50000
87
+ }
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 sha256:05cf1584d8e4680deb83fef38532b1350a6f1bd1b3547988b4ce2695f56709b8
3
+ size 1416305660
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": true,
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "</s>",
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": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01284e413c3825d9372e699a6d6a34adbef3cbcbb16ff5d3fc735e484e62f5f1
3
+ size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff