Hugging Face's logo

hugo-albert
/
roberta-ademamix-pos-accelerate

Safetensors
roberta
Model card Files Community
hugo-albert commited on
Commit
6b1bd6a
•
1 Parent(s): 6cdb024

Training in progress epoch 0

Browse files
Files changed (6) hide show
  1. config.json +164 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +57 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-large-bne",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "Z",
16
+ "1": "vsp",
17
+ "2": "vms",
18
+ "3": "vsg",
19
+ "4": "vss",
20
+ "5": "Fc",
21
+ "6": "vmn",
22
+ "7": "Fpt",
23
+ "8": "rn",
24
+ "9": "dp",
25
+ "10": "vas",
26
+ "11": "sp",
27
+ "12": "vsm",
28
+ "13": "vam",
29
+ "14": "Fs",
30
+ "15": "vai",
31
+ "16": "vag",
32
+ "17": "np",
33
+ "18": "Fd",
34
+ "19": "pi",
35
+ "20": "Fp",
36
+ "21": "pr",
37
+ "22": "Zm",
38
+ "23": "vap",
39
+ "24": "dt",
40
+ "25": "I",
41
+ "26": "ao",
42
+ "27": "Fh",
43
+ "28": "i",
44
+ "29": "de",
45
+ "30": "dn",
46
+ "31": "pe",
47
+ "32": "van",
48
+ "33": "aq",
49
+ "34": "nc",
50
+ "35": "dd",
51
+ "36": "da",
52
+ "37": "vmm",
53
+ "38": "vsn",
54
+ "39": "px",
55
+ "40": "vmi",
56
+ "41": "cc",
57
+ "42": "Fat",
58
+ "43": "pd",
59
+ "44": "pn",
60
+ "45": "Fe",
61
+ "46": "vmp",
62
+ "47": "Fz",
63
+ "48": "pp",
64
+ "49": "Faa",
65
+ "50": "Fpa",
66
+ "51": "W",
67
+ "52": "Fit",
68
+ "53": "Fx",
69
+ "54": "cs",
70
+ "55": "di",
71
+ "56": "Fg",
72
+ "57": "vmg",
73
+ "58": "Y",
74
+ "59": "rg",
75
+ "60": "p0",
76
+ "61": "Zp",
77
+ "62": "X",
78
+ "63": "Fia",
79
+ "64": "vsi",
80
+ "65": "pt"
81
+ },
82
+ "initializer_range": 0.02,
83
+ "intermediate_size": 4096,
84
+ "label2id": {
85
+ "Faa": 49,
86
+ "Fat": 42,
87
+ "Fc": 5,
88
+ "Fd": 18,
89
+ "Fe": 45,
90
+ "Fg": 56,
91
+ "Fh": 27,
92
+ "Fia": 63,
93
+ "Fit": 52,
94
+ "Fp": 20,
95
+ "Fpa": 50,
96
+ "Fpt": 7,
97
+ "Fs": 14,
98
+ "Fx": 53,
99
+ "Fz": 47,
100
+ "I": 25,
101
+ "W": 51,
102
+ "X": 62,
103
+ "Y": 58,
104
+ "Z": 0,
105
+ "Zm": 22,
106
+ "Zp": 61,
107
+ "ao": 26,
108
+ "aq": 33,
109
+ "cc": 41,
110
+ "cs": 54,
111
+ "da": 36,
112
+ "dd": 35,
113
+ "de": 29,
114
+ "di": 55,
115
+ "dn": 30,
116
+ "dp": 9,
117
+ "dt": 24,
118
+ "i": 28,
119
+ "nc": 34,
120
+ "np": 17,
121
+ "p0": 60,
122
+ "pd": 43,
123
+ "pe": 31,
124
+ "pi": 19,
125
+ "pn": 44,
126
+ "pp": 48,
127
+ "pr": 21,
128
+ "pt": 65,
129
+ "px": 39,
130
+ "rg": 59,
131
+ "rn": 8,
132
+ "sp": 11,
133
+ "vag": 16,
134
+ "vai": 15,
135
+ "vam": 13,
136
+ "van": 32,
137
+ "vap": 23,
138
+ "vas": 10,
139
+ "vmg": 57,
140
+ "vmi": 40,
141
+ "vmm": 37,
142
+ "vmn": 6,
143
+ "vmp": 46,
144
+ "vms": 2,
145
+ "vsg": 3,
146
+ "vsi": 64,
147
+ "vsm": 12,
148
+ "vsn": 38,
149
+ "vsp": 1,
150
+ "vss": 4
151
+ },
152
+ "layer_norm_eps": 1e-05,
153
+ "max_position_embeddings": 514,
154
+ "model_type": "roberta",
155
+ "num_attention_heads": 16,
156
+ "num_hidden_layers": 24,
157
+ "pad_token_id": 1,
158
+ "position_embedding_type": "absolute",
159
+ "torch_dtype": "float32",
160
+ "transformers_version": "4.44.2",
161
+ "type_vocab_size": 1,
162
+ "use_cache": true,
163
+ "vocab_size": 50262
164
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5874dff1b33e49f022d3b9aa3d09a88e31f8b8b6079ebf7421a16a5028a0989d
3
+ size 1417546912
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
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
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[MASK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": false,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff