Hugging Face's logo

liaad
/
propbank_br_srl_albertina_100m_portuguese_ptpt_encoder

Token Classification
Transformers
Safetensors
deberta
Inference Endpoints
Model card Files Community
arubenruben commited on
Commit
1e0b2f8
•
1 Parent(s): eb208d9

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. config.json +158 -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 +59 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
  9. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PORTULAN/albertina-100m-portuguese-ptpt-encoder",
3
+ "architectures": [
4
+ "DebertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "B-A0",
12
+ "1": "B-A1",
13
+ "2": "B-A2",
14
+ "3": "B-A3",
15
+ "4": "B-A4",
16
+ "5": "B-AM-ADV",
17
+ "6": "B-AM-CAU",
18
+ "7": "B-AM-DIR",
19
+ "8": "B-AM-DIS",
20
+ "9": "B-AM-EXT",
21
+ "10": "B-AM-LOC",
22
+ "11": "B-AM-MNR",
23
+ "12": "B-AM-NEG",
24
+ "13": "B-AM-PNC",
25
+ "14": "B-AM-PRD",
26
+ "15": "B-AM-REC",
27
+ "16": "B-AM-TMP",
28
+ "17": "B-C-A0",
29
+ "18": "B-C-A1",
30
+ "19": "B-C-A2",
31
+ "20": "B-C-A3",
32
+ "21": "B-C-AM-ADV",
33
+ "22": "B-C-AM-CAU",
34
+ "23": "B-C-AM-DIS",
35
+ "24": "B-C-AM-EXT",
36
+ "25": "B-C-AM-LOC",
37
+ "26": "B-C-AM-MNR",
38
+ "27": "B-C-AM-NEG",
39
+ "28": "B-C-AM-PRD",
40
+ "29": "B-C-AM-TMP",
41
+ "30": "B-C-V",
42
+ "31": "B-V",
43
+ "32": "I-A0",
44
+ "33": "I-A1",
45
+ "34": "I-A2",
46
+ "35": "I-A3",
47
+ "36": "I-A4",
48
+ "37": "I-AM-ADV",
49
+ "38": "I-AM-CAU",
50
+ "39": "I-AM-DIR",
51
+ "40": "I-AM-DIS",
52
+ "41": "I-AM-EXT",
53
+ "42": "I-AM-LOC",
54
+ "43": "I-AM-MNR",
55
+ "44": "I-AM-NEG",
56
+ "45": "I-AM-PNC",
57
+ "46": "I-AM-PRD",
58
+ "47": "I-AM-REC",
59
+ "48": "I-AM-TMP",
60
+ "49": "I-C-A0",
61
+ "50": "I-C-A1",
62
+ "51": "I-C-A2",
63
+ "52": "I-C-A3",
64
+ "53": "I-C-AM-ADV",
65
+ "54": "I-C-AM-CAU",
66
+ "55": "I-C-AM-LOC",
67
+ "56": "I-C-AM-MNR",
68
+ "57": "I-C-AM-PRD",
69
+ "58": "I-C-AM-TMP",
70
+ "59": "I-C-V",
71
+ "60": "O"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 3072,
75
+ "label2id": {
76
+ "B-A0": 0,
77
+ "B-A1": 1,
78
+ "B-A2": 2,
79
+ "B-A3": 3,
80
+ "B-A4": 4,
81
+ "B-AM-ADV": 5,
82
+ "B-AM-CAU": 6,
83
+ "B-AM-DIR": 7,
84
+ "B-AM-DIS": 8,
85
+ "B-AM-EXT": 9,
86
+ "B-AM-LOC": 10,
87
+ "B-AM-MNR": 11,
88
+ "B-AM-NEG": 12,
89
+ "B-AM-PNC": 13,
90
+ "B-AM-PRD": 14,
91
+ "B-AM-REC": 15,
92
+ "B-AM-TMP": 16,
93
+ "B-C-A0": 17,
94
+ "B-C-A1": 18,
95
+ "B-C-A2": 19,
96
+ "B-C-A3": 20,
97
+ "B-C-AM-ADV": 21,
98
+ "B-C-AM-CAU": 22,
99
+ "B-C-AM-DIS": 23,
100
+ "B-C-AM-EXT": 24,
101
+ "B-C-AM-LOC": 25,
102
+ "B-C-AM-MNR": 26,
103
+ "B-C-AM-NEG": 27,
104
+ "B-C-AM-PRD": 28,
105
+ "B-C-AM-TMP": 29,
106
+ "B-C-V": 30,
107
+ "B-V": 31,
108
+ "I-A0": 32,
109
+ "I-A1": 33,
110
+ "I-A2": 34,
111
+ "I-A3": 35,
112
+ "I-A4": 36,
113
+ "I-AM-ADV": 37,
114
+ "I-AM-CAU": 38,
115
+ "I-AM-DIR": 39,
116
+ "I-AM-DIS": 40,
117
+ "I-AM-EXT": 41,
118
+ "I-AM-LOC": 42,
119
+ "I-AM-MNR": 43,
120
+ "I-AM-NEG": 44,
121
+ "I-AM-PNC": 45,
122
+ "I-AM-PRD": 46,
123
+ "I-AM-REC": 47,
124
+ "I-AM-TMP": 48,
125
+ "I-C-A0": 49,
126
+ "I-C-A1": 50,
127
+ "I-C-A2": 51,
128
+ "I-C-A3": 52,
129
+ "I-C-AM-ADV": 53,
130
+ "I-C-AM-CAU": 54,
131
+ "I-C-AM-LOC": 55,
132
+ "I-C-AM-MNR": 56,
133
+ "I-C-AM-PRD": 57,
134
+ "I-C-AM-TMP": 58,
135
+ "I-C-V": 59,
136
+ "O": 60
137
+ },
138
+ "layer_norm_eps": 1e-07,
139
+ "max_position_embeddings": 512,
140
+ "max_relative_positions": -1,
141
+ "model_type": "deberta",
142
+ "num_attention_heads": 12,
143
+ "num_hidden_layers": 12,
144
+ "pad_token_id": 0,
145
+ "pooler_dropout": 0,
146
+ "pooler_hidden_act": "gelu",
147
+ "pooler_hidden_size": 768,
148
+ "pos_att_type": [
149
+ "c2p",
150
+ "p2c"
151
+ ],
152
+ "position_biased_input": false,
153
+ "relative_attention": true,
154
+ "torch_dtype": "float32",
155
+ "transformers_version": "4.39.3",
156
+ "type_vocab_size": 0,
157
+ "vocab_size": 50265
158
+ }
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:da9f8317518283255d35a91d20262df838a43195642b6f5bfeff51de06a5e118
3
+ size 554618516
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
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": "[SEP]",
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 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": true,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "[PAD]",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "[SEP]",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "[UNK]",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50264": {
38
+ "content": "[MASK]",
39
+ "lstrip": true,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "bos_token": "[CLS]",
47
+ "clean_up_tokenization_spaces": true,
48
+ "cls_token": "[CLS]",
49
+ "do_lower_case": false,
50
+ "eos_token": "[SEP]",
51
+ "errors": "replace",
52
+ "mask_token": "[MASK]",
53
+ "model_max_length": 512,
54
+ "pad_token": "[PAD]",
55
+ "sep_token": "[SEP]",
56
+ "tokenizer_class": "DebertaTokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "gpt2"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11051174e0f85314d2f8244227e24bb49af23d49a0c4c9a1e937637364eaac4d
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff