Text Generation
PEFT
PyTorch
llama
codys12 commited on
Commit
3ec102a
β€’
1 Parent(s): a7fe700

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -4
  2. tokenizer.json +6 -28
  3. tokenizer_config.json +1 -28
special_tokens_map.json CHANGED
@@ -3,10 +3,7 @@
3
  "▁<PRE>",
4
  "▁<MID>",
5
  "▁<SUF>",
6
- "▁<EOT>",
7
- ">>>>>>>",
8
- "=======",
9
- "<<<<<<<"
10
  ],
11
  "bos_token": "<s>",
12
  "eos_token": "</s>",
 
3
  "▁<PRE>",
4
  "▁<MID>",
5
  "▁<SUF>",
6
+ "▁<EOT>"
 
 
 
7
  ],
8
  "bos_token": "<s>",
9
  "eos_token": "</s>",
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
@@ -65,33 +70,6 @@
65
  "rstrip": true,
66
  "normalized": false,
67
  "special": true
68
- },
69
- {
70
- "id": 32016,
71
- "content": ">>>>>>>",
72
- "single_word": false,
73
- "lstrip": true,
74
- "rstrip": true,
75
- "normalized": false,
76
- "special": true
77
- },
78
- {
79
- "id": 32017,
80
- "content": "=======",
81
- "single_word": false,
82
- "lstrip": true,
83
- "rstrip": true,
84
- "normalized": false,
85
- "special": true
86
- },
87
- {
88
- "id": 32018,
89
- "content": "<<<<<<<",
90
- "single_word": false,
91
- "lstrip": true,
92
- "rstrip": true,
93
- "normalized": false,
94
- "special": true
95
  }
96
  ],
97
  "normalizer": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
70
  "rstrip": true,
71
  "normalized": false,
72
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
  }
74
  ],
75
  "normalizer": {
tokenizer_config.json CHANGED
@@ -55,40 +55,13 @@
55
  "rstrip": true,
56
  "single_word": false,
57
  "special": true
58
- },
59
- "32016": {
60
- "content": ">>>>>>>",
61
- "lstrip": true,
62
- "normalized": false,
63
- "rstrip": true,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "32017": {
68
- "content": "=======",
69
- "lstrip": true,
70
- "normalized": false,
71
- "rstrip": true,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "32018": {
76
- "content": "<<<<<<<",
77
- "lstrip": true,
78
- "normalized": false,
79
- "rstrip": true,
80
- "single_word": false,
81
- "special": true
82
  }
83
  },
84
  "additional_special_tokens": [
85
  "▁<PRE>",
86
  "▁<MID>",
87
  "▁<SUF>",
88
- "▁<EOT>",
89
- ">>>>>>>",
90
- "=======",
91
- "<<<<<<<"
92
  ],
93
  "bos_token": "<s>",
94
  "clean_up_tokenization_spaces": false,
 
55
  "rstrip": true,
56
  "single_word": false,
57
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  }
59
  },
60
  "additional_special_tokens": [
61
  "▁<PRE>",
62
  "▁<MID>",
63
  "▁<SUF>",
64
+ "▁<EOT>"
 
 
 
65
  ],
66
  "bos_token": "<s>",
67
  "clean_up_tokenization_spaces": false,