Hugging Face's logo

liaad
/
propbank_br_srl_albertina_900m_portuguese_ptpt_encoder

Token Classification
Transformers
Safetensors
deberta-v2
Inference Endpoints
Model card Files Community
arubenruben commited on
Commit
5992eba
•
1 Parent(s): e288559

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. config.json +164 -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 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "B-A0",
15
+ "1": "B-A1",
16
+ "2": "B-A2",
17
+ "3": "B-A3",
18
+ "4": "B-A4",
19
+ "5": "B-AM-ADV",
20
+ "6": "B-AM-CAU",
21
+ "7": "B-AM-DIR",
22
+ "8": "B-AM-DIS",
23
+ "9": "B-AM-EXT",
24
+ "10": "B-AM-LOC",
25
+ "11": "B-AM-MNR",
26
+ "12": "B-AM-NEG",
27
+ "13": "B-AM-PNC",
28
+ "14": "B-AM-PRD",
29
+ "15": "B-AM-REC",
30
+ "16": "B-AM-TMP",
31
+ "17": "B-C-A0",
32
+ "18": "B-C-A1",
33
+ "19": "B-C-A2",
34
+ "20": "B-C-A3",
35
+ "21": "B-C-AM-ADV",
36
+ "22": "B-C-AM-CAU",
37
+ "23": "B-C-AM-DIS",
38
+ "24": "B-C-AM-EXT",
39
+ "25": "B-C-AM-LOC",
40
+ "26": "B-C-AM-MNR",
41
+ "27": "B-C-AM-NEG",
42
+ "28": "B-C-AM-PRD",
43
+ "29": "B-C-AM-TMP",
44
+ "30": "B-C-V",
45
+ "31": "B-V",
46
+ "32": "I-A0",
47
+ "33": "I-A1",
48
+ "34": "I-A2",
49
+ "35": "I-A3",
50
+ "36": "I-A4",
51
+ "37": "I-AM-ADV",
52
+ "38": "I-AM-CAU",
53
+ "39": "I-AM-DIR",
54
+ "40": "I-AM-DIS",
55
+ "41": "I-AM-EXT",
56
+ "42": "I-AM-LOC",
57
+ "43": "I-AM-MNR",
58
+ "44": "I-AM-NEG",
59
+ "45": "I-AM-PNC",
60
+ "46": "I-AM-PRD",
61
+ "47": "I-AM-REC",
62
+ "48": "I-AM-TMP",
63
+ "49": "I-C-A0",
64
+ "50": "I-C-A1",
65
+ "51": "I-C-A2",
66
+ "52": "I-C-A3",
67
+ "53": "I-C-AM-ADV",
68
+ "54": "I-C-AM-CAU",
69
+ "55": "I-C-AM-LOC",
70
+ "56": "I-C-AM-MNR",
71
+ "57": "I-C-AM-PRD",
72
+ "58": "I-C-AM-TMP",
73
+ "59": "I-C-V",
74
+ "60": "O"
75
+ },
76
+ "initializer_range": 0.02,
77
+ "intermediate_size": 6144,
78
+ "label2id": {
79
+ "B-A0": 0,
80
+ "B-A1": 1,
81
+ "B-A2": 2,
82
+ "B-A3": 3,
83
+ "B-A4": 4,
84
+ "B-AM-ADV": 5,
85
+ "B-AM-CAU": 6,
86
+ "B-AM-DIR": 7,
87
+ "B-AM-DIS": 8,
88
+ "B-AM-EXT": 9,
89
+ "B-AM-LOC": 10,
90
+ "B-AM-MNR": 11,
91
+ "B-AM-NEG": 12,
92
+ "B-AM-PNC": 13,
93
+ "B-AM-PRD": 14,
94
+ "B-AM-REC": 15,
95
+ "B-AM-TMP": 16,
96
+ "B-C-A0": 17,
97
+ "B-C-A1": 18,
98
+ "B-C-A2": 19,
99
+ "B-C-A3": 20,
100
+ "B-C-AM-ADV": 21,
101
+ "B-C-AM-CAU": 22,
102
+ "B-C-AM-DIS": 23,
103
+ "B-C-AM-EXT": 24,
104
+ "B-C-AM-LOC": 25,
105
+ "B-C-AM-MNR": 26,
106
+ "B-C-AM-NEG": 27,
107
+ "B-C-AM-PRD": 28,
108
+ "B-C-AM-TMP": 29,
109
+ "B-C-V": 30,
110
+ "B-V": 31,
111
+ "I-A0": 32,
112
+ "I-A1": 33,
113
+ "I-A2": 34,
114
+ "I-A3": 35,
115
+ "I-A4": 36,
116
+ "I-AM-ADV": 37,
117
+ "I-AM-CAU": 38,
118
+ "I-AM-DIR": 39,
119
+ "I-AM-DIS": 40,
120
+ "I-AM-EXT": 41,
121
+ "I-AM-LOC": 42,
122
+ "I-AM-MNR": 43,
123
+ "I-AM-NEG": 44,
124
+ "I-AM-PNC": 45,
125
+ "I-AM-PRD": 46,
126
+ "I-AM-REC": 47,
127
+ "I-AM-TMP": 48,
128
+ "I-C-A0": 49,
129
+ "I-C-A1": 50,
130
+ "I-C-A2": 51,
131
+ "I-C-A3": 52,
132
+ "I-C-AM-ADV": 53,
133
+ "I-C-AM-CAU": 54,
134
+ "I-C-AM-LOC": 55,
135
+ "I-C-AM-MNR": 56,
136
+ "I-C-AM-PRD": 57,
137
+ "I-C-AM-TMP": 58,
138
+ "I-C-V": 59,
139
+ "O": 60
140
+ },
141
+ "layer_norm_eps": 1e-07,
142
+ "max_position_embeddings": 512,
143
+ "max_relative_positions": -1,
144
+ "model_type": "deberta-v2",
145
+ "norm_rel_ebd": "layer_norm",
146
+ "num_attention_heads": 24,
147
+ "num_hidden_layers": 24,
148
+ "pad_token_id": 0,
149
+ "pooler_dropout": 0,
150
+ "pooler_hidden_act": "gelu",
151
+ "pooler_hidden_size": 1536,
152
+ "pos_att_type": [
153
+ "p2c",
154
+ "c2p"
155
+ ],
156
+ "position_biased_input": false,
157
+ "position_buckets": 256,
158
+ "relative_attention": true,
159
+ "share_att_key": true,
160
+ "torch_dtype": "float32",
161
+ "transformers_version": "4.39.3",
162
+ "type_vocab_size": 0,
163
+ "vocab_size": 128100
164
+ }
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 sha256:4447de8e3b46204fdbac5da0dcc3f8177664e34311056813d82e06e5f6f87c66
3
+ size 3538797348
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": true,
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 sha256:7715bb6c057601d2a4217293f459b6cc04577577010c1f22ab5e389eb33d65eb
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