Hugging Face's logo

Nuri-Tas
/
roberturk-base

Feature Extraction
Transformers
Safetensors
roberta
text-embeddings-inference
Inference Endpoints
Model card Files Community
Nuri-Tas commited on
Commit
64e303c
·
1 Parent(s): 8c63427

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +6 -6
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +5 -5
  5. vocab.json +0 -0
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -2,21 +2,21 @@
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
  },
@@ -30,21 +30,21 @@
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
  }
 
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
  },
 
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "0": {
5
  "content": "<s>",
6
  "lstrip": false,
7
- "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
@@ -12,7 +12,7 @@
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
@@ -20,7 +20,7 @@
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
@@ -28,12 +28,12 @@
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
- "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "4": {
37
  "content": "<mask>",
38
  "lstrip": true,
39
  "normalized": false,
 
4
  "0": {
5
  "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
 
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
 
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "50265": {
37
  "content": "<mask>",
38
  "lstrip": true,
39
  "normalized": false,
vocab.json CHANGED
The diff for this file is too large to render. See raw diff