Hugging Face's logo

santoshpandey
/
indic-nepali-finetune-colab

Transformers
Model card Files Community
santoshpandey commited on
Commit
3ed904b
·
verified ·
1 Parent(s): ec64338

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +4 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +3 -7
added_tokens.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
- "</s>": 73,
3
- "<s>": 72
 
 
4
  }
 
1
  {
2
+ "</s>": 69,
3
+ "<s>": 68,
4
+ "[PAD]": 67,
5
+ "[UNK]": 66
6
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "70": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "71": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "72": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "73": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "66": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "67": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "68": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "69": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
- "[PAD]": 71,
3
- "[UNK]": 70,
4
- "|": 0,
5
  "ँ": 1,
6
  "ं": 2,
7
  "अ": 3,
@@ -58,7 +57,6 @@
58
  "ो": 54,
59
  "ौ": 55,
60
  "्": 56,
61
- "।": 57,
62
  "०": 58,
63
  "१": 59,
64
  "२": 60,
@@ -68,7 +66,5 @@
68
  "६": 64,
69
  "७": 65,
70
  "८": 66,
71
- "९": 67,
72
- "‌": 68,
73
- "‍": 69
74
  }
 
1
  {
2
+ "[PAD]": 67,
3
+ "[UNK]": 66,
 
4
  "ँ": 1,
5
  "ं": 2,
6
  "अ": 3,
 
57
  "ो": 54,
58
  "ौ": 55,
59
  "्": 56,
 
60
  "०": 58,
61
  "१": 59,
62
  "२": 60,
 
66
  "६": 64,
67
  "७": 65,
68
  "८": 66,
69
+ "९": 67
 
 
70
  }