Hugging Face's logo

liaad
/
NER-harem-albertina-900m-portuguese-ptpt-encoder

Token Classification
Transformers
Safetensors
Portuguese
deberta-v2
Inference Endpoints
Model card Files Community
arubenruben commited on
Commit
cf533d7
•
1 Parent(s): 262fe82

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +84 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +51 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +59 -0
  6. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PORTULAN/albertina-900m-portuguese-ptpt-encoder",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_head_size": 64,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "conv_act": "gelu",
9
+ "conv_kernel_size": 3,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1536,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-PESSOA",
16
+ "2": "I-PESSOA",
17
+ "3": "B-ORGANIZACAO",
18
+ "4": "I-ORGANIZACAO",
19
+ "5": "B-LOCAL",
20
+ "6": "I-LOCAL",
21
+ "7": "B-TEMPO",
22
+ "8": "I-TEMPO",
23
+ "9": "B-VALOR",
24
+ "10": "I-VALOR",
25
+ "11": "B-ABSTRACCAO",
26
+ "12": "I-ABSTRACCAO",
27
+ "13": "B-ACONTECIMENTO",
28
+ "14": "I-ACONTECIMENTO",
29
+ "15": "B-COISA",
30
+ "16": "I-COISA",
31
+ "17": "B-OBRA",
32
+ "18": "I-OBRA",
33
+ "19": "B-OUTRO",
34
+ "20": "I-OUTRO"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 6144,
38
+ "label2id": {
39
+ "B-ABSTRACCAO": 11,
40
+ "B-ACONTECIMENTO": 13,
41
+ "B-COISA": 15,
42
+ "B-LOCAL": 5,
43
+ "B-OBRA": 17,
44
+ "B-ORGANIZACAO": 3,
45
+ "B-OUTRO": 19,
46
+ "B-PESSOA": 1,
47
+ "B-TEMPO": 7,
48
+ "B-VALOR": 9,
49
+ "I-ABSTRACCAO": 12,
50
+ "I-ACONTECIMENTO": 14,
51
+ "I-COISA": 16,
52
+ "I-LOCAL": 6,
53
+ "I-OBRA": 18,
54
+ "I-ORGANIZACAO": 4,
55
+ "I-OUTRO": 20,
56
+ "I-PESSOA": 2,
57
+ "I-TEMPO": 8,
58
+ "I-VALOR": 10,
59
+ "O": 0
60
+ },
61
+ "layer_norm_eps": 1e-07,
62
+ "max_position_embeddings": 512,
63
+ "max_relative_positions": -1,
64
+ "model_type": "deberta-v2",
65
+ "norm_rel_ebd": "layer_norm",
66
+ "num_attention_heads": 24,
67
+ "num_hidden_layers": 24,
68
+ "pad_token_id": 0,
69
+ "pooler_dropout": 0,
70
+ "pooler_hidden_act": "gelu",
71
+ "pooler_hidden_size": 1536,
72
+ "pos_att_type": [
73
+ "p2c",
74
+ "c2p"
75
+ ],
76
+ "position_biased_input": false,
77
+ "position_buckets": 256,
78
+ "relative_attention": true,
79
+ "share_att_key": true,
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.38.2",
82
+ "type_vocab_size": 0,
83
+ "vocab_size": 128100
84
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64286e388da178037d6d9909a5588c3cac82ee2c65f2c9a4cb33660d88d1c70d
3
+ size 3538551420
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": false,
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 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128000": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f352959f67c179d14ed753e67a59ec9b879d5b3c8bb30c5818f5196074b3bf
3
+ size 5048