HiTZ
/

Iker commited on
Commit
d8058a7
1 Parent(s): 37e097e

Upload tokenizer

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,35 +1,31 @@
1
  ---
 
 
 
 
2
  license: apache-2.0
3
- widget:
4
- - text: >-
5
- <Disease> Torsade de pointes ventricular tachycardia during low dose
6
- intermittent dobutamine treatment in a patient with dilated cardiomyopathy
7
- and congestive heart failure .
8
- - text: >-
9
- <ClinicalEntity> Ecográficamente se observan tres nódulos tumorales
10
- independientes y bien delimitados : dos de ellos heterogéneos , sólidos , de
11
- 20 y 33 mm de diámetros , con áreas quísticas y calcificaciones .
12
- - text: >-
13
- <ClinicalEntity> On notait une hyperlordose lombaire avec une contracture
14
- permanente des muscles paravertébraux , de l abdomen et des deux membres
15
- inférieurs .
16
- - text: >-
17
- <ClinicalEntity> Nell ’ anamnesi patologica era riferita ipertensione
18
- arteriosa controllata con terapia medica
19
  library_name: transformers
20
- pipeline_tag: text2text-generation
21
  tags:
22
  - medical
23
  - multilingual
24
  - medic
 
25
  datasets:
26
  - HiTZ/Multilingual-Medical-Corpus
27
  - HiTZ/multilingual-abstrct
28
- language:
29
- - es
30
- - en
31
- - fr
32
- base_model: HiTZ/Medical-mT5-xl
 
 
 
 
 
 
 
 
33
  ---
34
 
35
  <p align="center">
 
1
  ---
2
+ language:
3
+ - es
4
+ - en
5
+ - fr
6
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  library_name: transformers
 
8
  tags:
9
  - medical
10
  - multilingual
11
  - medic
12
+ base_model: HiTZ/Medical-mT5-xl
13
  datasets:
14
  - HiTZ/Multilingual-Medical-Corpus
15
  - HiTZ/multilingual-abstrct
16
+ widget:
17
+ - text: <Disease> Torsade de pointes ventricular tachycardia during low dose intermittent
18
+ dobutamine treatment in a patient with dilated cardiomyopathy and congestive heart
19
+ failure .
20
+ - text: '<ClinicalEntity> Ecográficamente se observan tres nódulos tumorales independientes
21
+ y bien delimitados : dos de ellos heterogéneos , sólidos , de 20 y 33 mm de diámetros
22
+ , con áreas quísticas y calcificaciones .'
23
+ - text: <ClinicalEntity> On notait une hyperlordose lombaire avec une contracture
24
+ permanente des muscles paravertébraux , de l abdomen et des deux membres inférieurs
25
+ .
26
+ - text: <ClinicalEntity> Nell ’ anamnesi patologica era riferita ipertensione arteriosa
27
+ controllata con terapia medica
28
+ pipeline_tag: text2text-generation
29
  ---
30
 
31
  <p align="center">
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</Chemical>": 250117,
3
+ "</Claim>": 250113,
4
+ "</ClinicalEntity>": 250111,
5
+ "</Dis>": 250112,
6
+ "</Disease>": 250116,
7
+ "</DiseaseNCBI>": 250115,
8
+ "</NORMALIZABLES>": 250120,
9
+ "</NO_NORMALIZABLES>": 250118,
10
+ "</PROTEINAS>": 250119,
11
+ "</Premise>": 250114,
12
+ "</UNCLEAR>": 250121,
13
+ "<Chemical>": 250106,
14
+ "<Claim>": 250102,
15
+ "<ClinicalEntity>": 250100,
16
+ "<Dis>": 250101,
17
+ "<Disease>": 250105,
18
+ "<DiseaseNCBI>": 250104,
19
+ "<NORMALIZABLES>": 250109,
20
+ "<NO_NORMALIZABLES>": 250107,
21
+ "<PROTEINAS>": 250108,
22
+ "<Premise>": 250103,
23
+ "<UNCLEAR>": 250110
24
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1cdb0dbb7e955224c5369e80d8c9a9d15d307d5419d97e49d615949986a336
3
+ size 16319362
tokenizer_config.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_eos_token": 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": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "250100": {
29
+ "content": "<ClinicalEntity>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "250101": {
37
+ "content": "<Dis>",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "250102": {
45
+ "content": "<Claim>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "250103": {
53
+ "content": "<Premise>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "250104": {
61
+ "content": "<DiseaseNCBI>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "250105": {
69
+ "content": "<Disease>",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "250106": {
77
+ "content": "<Chemical>",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "250107": {
85
+ "content": "<NO_NORMALIZABLES>",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "250108": {
93
+ "content": "<PROTEINAS>",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "250109": {
101
+ "content": "<NORMALIZABLES>",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "250110": {
109
+ "content": "<UNCLEAR>",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "250111": {
117
+ "content": "</ClinicalEntity>",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "250112": {
125
+ "content": "</Dis>",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "250113": {
133
+ "content": "</Claim>",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "250114": {
141
+ "content": "</Premise>",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "250115": {
149
+ "content": "</DiseaseNCBI>",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "250116": {
157
+ "content": "</Disease>",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "250117": {
165
+ "content": "</Chemical>",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "250118": {
173
+ "content": "</NO_NORMALIZABLES>",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "250119": {
181
+ "content": "</PROTEINAS>",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "250120": {
189
+ "content": "</NORMALIZABLES>",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "250121": {
197
+ "content": "</UNCLEAR>",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "additional_special_tokens": [],
206
+ "clean_up_tokenization_spaces": true,
207
+ "eos_token": "</s>",
208
+ "extra_ids": 0,
209
+ "legacy": true,
210
+ "model_max_length": 1000000000000000019884624838656,
211
+ "pad_token": "<pad>",
212
+ "sp_model_kwargs": {},
213
+ "tokenizer_class": "T5Tokenizer",
214
+ "unk_token": "<unk>"
215
+ }