KingLLM commited on
Commit
9ab7023
·
verified ·
1 Parent(s): c91eefe

Upload tokenizer

Browse files
added_tokens.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "Bioderma": 250014,
3
  "Cerave": 250002,
 
4
  "Drunk Elephant": 250013,
5
  "Eucerin": 250021,
6
  "EucerinSPF 50": 250011,
@@ -9,6 +10,7 @@
9
  "Hydro Boost Water Gel": 250006,
10
  "L'Oréal": 250010,
11
  "La Roche-Posay": 250004,
 
12
  "Myntra": 250019,
13
  "Neutrogena": 250005,
14
  "Niacinamide": 250007,
 
1
  {
2
  "Bioderma": 250014,
3
  "Cerave": 250002,
4
+ "Costco": 250024,
5
  "Drunk Elephant": 250013,
6
  "Eucerin": 250021,
7
  "EucerinSPF 50": 250011,
 
10
  "Hydro Boost Water Gel": 250006,
11
  "L'Oréal": 250010,
12
  "La Roche-Posay": 250004,
13
+ "Mart": 250023,
14
  "Myntra": 250019,
15
  "Neutrogena": 250005,
16
  "Niacinamide": 250007,
special_tokens_map.json CHANGED
@@ -1,7 +1,25 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
@@ -9,7 +27,25 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "<mask>",
25
  "lstrip": true,
 
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": "</s>",
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e713901bac6b865d60cb5e0af6742c24d89c104c5edfcfd3fd8ade1787c1d0c
3
- size 17086930
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986d592584f26c7bfbfa2fa7ec773b063a05ad820a384fed3cc5537931bff31a
3
+ size 17087294
tokenizer_config.json CHANGED
@@ -215,6 +215,22 @@
215
  "rstrip": false,
216
  "single_word": false,
217
  "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
218
  }
219
  },
220
  "bos_token": "<s>",
@@ -223,9 +239,13 @@
223
  "eos_token": "</s>",
224
  "extra_special_tokens": {},
225
  "mask_token": "<mask>",
 
226
  "model_max_length": 512,
227
  "pad_token": "<pad>",
228
  "sep_token": "</s>",
 
229
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
230
  "unk_token": "<unk>"
231
  }
 
215
  "rstrip": false,
216
  "single_word": false,
217
  "special": false
218
+ },
219
+ "250023": {
220
+ "content": "Mart",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "250024": {
228
+ "content": "Costco",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
  }
235
  },
236
  "bos_token": "<s>",
 
239
  "eos_token": "</s>",
240
  "extra_special_tokens": {},
241
  "mask_token": "<mask>",
242
+ "max_length": 512,
243
  "model_max_length": 512,
244
  "pad_token": "<pad>",
245
  "sep_token": "</s>",
246
+ "stride": 0,
247
  "tokenizer_class": "XLMRobertaTokenizer",
248
+ "truncation_side": "right",
249
+ "truncation_strategy": "longest_first",
250
  "unk_token": "<unk>"
251
  }