Token Classification
Transformers
PyTorch
Catalan
roberta
crodri commited on
Commit
94bd8b5
·
1 Parent(s): 1e83f6e

initial file upload

Browse files
all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_precision": 0.8206999626354465, "eval_recall": 0.8523237314224367, "eval_f1": 0.8362129681918261, "eval_accuracy": 0.9714466047158264}
config.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "projecte-aina/roberta-large-ca-v2",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "I-product-vehicle",
16
+ "2": "I-organization-sportsteam",
17
+ "3": "B-location-road/railway/highway/transit",
18
+ "4": "I-CW-other",
19
+ "5": "B-event-other",
20
+ "6": "I-CW-painting",
21
+ "7": "I-person-group",
22
+ "8": "B-CW-music",
23
+ "9": "I-location-other",
24
+ "10": "B-organization-religious",
25
+ "11": "I-product-E-device",
26
+ "12": "B-product-software",
27
+ "13": "B-event-attack/terrorism/militaryconflict",
28
+ "14": "B-organization-politicalparty",
29
+ "15": "B-person-scholar/scientist",
30
+ "16": "I-person-artist/author",
31
+ "17": "B-CW-other",
32
+ "18": "I-person-influencer",
33
+ "19": "B-event-protest",
34
+ "20": "I-building-other",
35
+ "21": "I-organization-other",
36
+ "22": "B-organization-sportsteam",
37
+ "23": "B-organization-media",
38
+ "24": "I-event-disaster",
39
+ "25": "I-organization-privatecompany",
40
+ "26": "I-event-other",
41
+ "27": "B-location-other",
42
+ "28": "B-product-clothing",
43
+ "29": "B-organization-education",
44
+ "30": "B-building-sportsfacility",
45
+ "31": "I-building-shops",
46
+ "32": "I-location-park",
47
+ "33": "B-organization-government",
48
+ "34": "I-person-politician",
49
+ "35": "B-building-airport",
50
+ "36": "B-CW-writtenart",
51
+ "37": "B-location-park",
52
+ "38": "B-location-island",
53
+ "39": "I-building-hotel",
54
+ "40": "B-Other",
55
+ "41": "B-organization-other",
56
+ "42": "B-person-group",
57
+ "43": "B-event-disaster",
58
+ "44": "I-organization-onlinebusiness",
59
+ "45": "B-product-consumer_good",
60
+ "46": "I-CW-broadcastprogram",
61
+ "47": "I-person-other",
62
+ "48": "B-building-hotel",
63
+ "49": "B-product-vehicle",
64
+ "50": "I-organization-politicalparty",
65
+ "51": "B-event-political",
66
+ "52": "B-location-mountain",
67
+ "53": "I-organization-religious",
68
+ "54": "B-GPE",
69
+ "55": "I-location-mountain",
70
+ "56": "I-CW-film",
71
+ "57": "I-CW-music",
72
+ "58": "B-location-bodiesofwater",
73
+ "59": "I-location-road/railway/highway/transit",
74
+ "60": "I-event-sportsevent",
75
+ "61": "B-organization-onlinebusiness",
76
+ "62": "I-organization-government",
77
+ "63": "I-person-actor/director",
78
+ "64": "B-person-athlete",
79
+ "65": "I-organization-education",
80
+ "66": "I-event-attack/terrorism/militaryconflict",
81
+ "67": "I-product-consumer_good",
82
+ "68": "I-building-hospital",
83
+ "69": "B-building-shops",
84
+ "70": "I-event-political",
85
+ "71": "I-building-religious",
86
+ "72": "B-CW-painting",
87
+ "73": "I-building-sportsfacility",
88
+ "74": "I-event-protest",
89
+ "75": "B-building-restaurant",
90
+ "76": "B-person-politician",
91
+ "77": "B-product-other",
92
+ "78": "I-CW-writtenart",
93
+ "79": "I-product-other",
94
+ "80": "I-product-food",
95
+ "81": "B-event-sportsevent",
96
+ "82": "B-CW-film",
97
+ "83": "I-product-clothing",
98
+ "84": "B-CW-broadcastprogram",
99
+ "85": "I-product-software",
100
+ "86": "I-person-athlete",
101
+ "87": "B-product-E-device",
102
+ "88": "B-person-actor/director",
103
+ "89": "B-building-religious",
104
+ "90": "I-GPE",
105
+ "91": "B-person-artist/author",
106
+ "92": "B-organization-privatecompany",
107
+ "93": "I-building-restaurant",
108
+ "94": "B-building-hospital",
109
+ "95": "I-Other",
110
+ "96": "I-person-scholar/scientist",
111
+ "97": "B-person-influencer",
112
+ "98": "B-person-other",
113
+ "99": "I-location-bodiesofwater",
114
+ "100": "I-building-airport",
115
+ "101": "I-organization-media",
116
+ "102": "B-product-food",
117
+ "103": "B-building-other",
118
+ "104": "B-building-governmentfacility",
119
+ "105": "I-building-governmentfacility",
120
+ "106": "I-location-island"
121
+ },
122
+ "initializer_range": 0.02,
123
+ "intermediate_size": 4096,
124
+ "label2id": {
125
+ "B-CW-broadcastprogram": 84,
126
+ "B-CW-film": 82,
127
+ "B-CW-music": 8,
128
+ "B-CW-other": 17,
129
+ "B-CW-painting": 72,
130
+ "B-CW-writtenart": 36,
131
+ "B-GPE": 54,
132
+ "B-Other": 40,
133
+ "B-building-airport": 35,
134
+ "B-building-governmentfacility": 104,
135
+ "B-building-hospital": 94,
136
+ "B-building-hotel": 48,
137
+ "B-building-other": 103,
138
+ "B-building-religious": 89,
139
+ "B-building-restaurant": 75,
140
+ "B-building-shops": 69,
141
+ "B-building-sportsfacility": 30,
142
+ "B-event-attack/terrorism/militaryconflict": 13,
143
+ "B-event-disaster": 43,
144
+ "B-event-other": 5,
145
+ "B-event-political": 51,
146
+ "B-event-protest": 19,
147
+ "B-event-sportsevent": 81,
148
+ "B-location-bodiesofwater": 58,
149
+ "B-location-island": 38,
150
+ "B-location-mountain": 52,
151
+ "B-location-other": 27,
152
+ "B-location-park": 37,
153
+ "B-location-road/railway/highway/transit": 3,
154
+ "B-organization-education": 29,
155
+ "B-organization-government": 33,
156
+ "B-organization-media": 23,
157
+ "B-organization-onlinebusiness": 61,
158
+ "B-organization-other": 41,
159
+ "B-organization-politicalparty": 14,
160
+ "B-organization-privatecompany": 92,
161
+ "B-organization-religious": 10,
162
+ "B-organization-sportsteam": 22,
163
+ "B-person-actor/director": 88,
164
+ "B-person-artist/author": 91,
165
+ "B-person-athlete": 64,
166
+ "B-person-group": 42,
167
+ "B-person-influencer": 97,
168
+ "B-person-other": 98,
169
+ "B-person-politician": 76,
170
+ "B-person-scholar/scientist": 15,
171
+ "B-product-E-device": 87,
172
+ "B-product-clothing": 28,
173
+ "B-product-consumer_good": 45,
174
+ "B-product-food": 102,
175
+ "B-product-other": 77,
176
+ "B-product-software": 12,
177
+ "B-product-vehicle": 49,
178
+ "I-CW-broadcastprogram": 46,
179
+ "I-CW-film": 56,
180
+ "I-CW-music": 57,
181
+ "I-CW-other": 4,
182
+ "I-CW-painting": 6,
183
+ "I-CW-writtenart": 78,
184
+ "I-GPE": 90,
185
+ "I-Other": 95,
186
+ "I-building-airport": 100,
187
+ "I-building-governmentfacility": 105,
188
+ "I-building-hospital": 68,
189
+ "I-building-hotel": 39,
190
+ "I-building-other": 20,
191
+ "I-building-religious": 71,
192
+ "I-building-restaurant": 93,
193
+ "I-building-shops": 31,
194
+ "I-building-sportsfacility": 73,
195
+ "I-event-attack/terrorism/militaryconflict": 66,
196
+ "I-event-disaster": 24,
197
+ "I-event-other": 26,
198
+ "I-event-political": 70,
199
+ "I-event-protest": 74,
200
+ "I-event-sportsevent": 60,
201
+ "I-location-bodiesofwater": 99,
202
+ "I-location-island": 106,
203
+ "I-location-mountain": 55,
204
+ "I-location-other": 9,
205
+ "I-location-park": 32,
206
+ "I-location-road/railway/highway/transit": 59,
207
+ "I-organization-education": 65,
208
+ "I-organization-government": 62,
209
+ "I-organization-media": 101,
210
+ "I-organization-onlinebusiness": 44,
211
+ "I-organization-other": 21,
212
+ "I-organization-politicalparty": 50,
213
+ "I-organization-privatecompany": 25,
214
+ "I-organization-religious": 53,
215
+ "I-organization-sportsteam": 2,
216
+ "I-person-actor/director": 63,
217
+ "I-person-artist/author": 16,
218
+ "I-person-athlete": 86,
219
+ "I-person-group": 7,
220
+ "I-person-influencer": 18,
221
+ "I-person-other": 47,
222
+ "I-person-politician": 34,
223
+ "I-person-scholar/scientist": 96,
224
+ "I-product-E-device": 11,
225
+ "I-product-clothing": 83,
226
+ "I-product-consumer_good": 67,
227
+ "I-product-food": 80,
228
+ "I-product-other": 79,
229
+ "I-product-software": 85,
230
+ "I-product-vehicle": 1,
231
+ "O": 0
232
+ },
233
+ "layer_norm_eps": 1e-05,
234
+ "max_position_embeddings": 514,
235
+ "model_type": "roberta",
236
+ "num_attention_heads": 16,
237
+ "num_hidden_layers": 24,
238
+ "pad_token_id": 1,
239
+ "position_embedding_type": "absolute",
240
+ "torch_dtype": "float32",
241
+ "transformers_version": "4.31.0",
242
+ "type_vocab_size": 1,
243
+ "use_cache": true,
244
+ "vocab_size": 50262
245
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb2e39405ed613ac638e75ad71e1b7fbb69b3f29047dce536d643807d7df33d1
3
+ size 1417801897
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "max_len": 512,
38
+ "model_max_length": 512,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff