Hugging Face's logo

ccore
/
getcode-350m

Text Generation
Transformers
TensorBoard
Safetensors
opt
text-generation-inference
Model card Files
xet
Metrics Community
ccore commited on
Commit
90e6a0a
·
verified ·
1 Parent(s): 7e840f2

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +7 -26
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +11 -149
  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
@@ -1,42 +1,23 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|endoftext|>",
4
- "<|im_start|>",
5
- "<|im_end|>",
6
- "<repo_name>",
7
- "<reponame>",
8
- "<file_sep>",
9
- "<filename>",
10
- "<gh_stars>",
11
- "<issue_start>",
12
- "<issue_comment>",
13
- "<issue_closed>",
14
- "<jupyter_start>",
15
- "<jupyter_text>",
16
- "<jupyter_code>",
17
- "<jupyter_output>",
18
- "<jupyter_script>",
19
- "<empty_output>"
20
- ],
21
  "bos_token": {
22
- "content": "<|endoftext|>",
23
  "lstrip": false,
24
- "normalized": false,
25
  "rstrip": false,
26
  "single_word": false
27
  },
28
  "eos_token": {
29
- "content": "<|endoftext|>",
30
  "lstrip": false,
31
- "normalized": false,
32
  "rstrip": false,
33
  "single_word": false
34
  },
35
- "pad_token": "<|endoftext|>",
36
  "unk_token": {
37
- "content": "<|endoftext|>",
38
  "lstrip": false,
39
- "normalized": false,
40
  "rstrip": false,
41
  "single_word": false
42
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
+ "content": "</s>",
4
  "lstrip": false,
5
+ "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "</s>",
11
  "lstrip": false,
12
+ "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "</s>",
17
  "unk_token": {
18
+ "content": "</s>",
19
  "lstrip": false,
20
+ "normalized": true,
21
  "rstrip": false,
22
  "single_word": false
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,169 +1,31 @@
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "0": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
  "1": {
13
- "content": "<|im_start|>",
14
  "lstrip": false,
15
- "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
  "2": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<repo_name>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<reponame>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<file_sep>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "6": {
53
- "content": "<filename>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "7": {
61
- "content": "<gh_stars>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "8": {
69
- "content": "<issue_start>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "9": {
77
- "content": "<issue_comment>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "10": {
85
- "content": "<issue_closed>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "11": {
93
- "content": "<jupyter_start>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "12": {
101
- "content": "<jupyter_text>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "13": {
109
- "content": "<jupyter_code>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "14": {
117
- "content": "<jupyter_output>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "15": {
125
- "content": "<jupyter_script>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "16": {
133
- "content": "<empty_output>",
134
  "lstrip": false,
135
- "normalized": false,
136
  "rstrip": false,
137
  "single_word": false,
138
  "special": true
139
  }
140
  },
141
- "additional_special_tokens": [
142
- "<|endoftext|>",
143
- "<|im_start|>",
144
- "<|im_end|>",
145
- "<repo_name>",
146
- "<reponame>",
147
- "<file_sep>",
148
- "<filename>",
149
- "<gh_stars>",
150
- "<issue_start>",
151
- "<issue_comment>",
152
- "<issue_closed>",
153
- "<jupyter_start>",
154
- "<jupyter_text>",
155
- "<jupyter_code>",
156
- "<jupyter_output>",
157
- "<jupyter_script>",
158
- "<empty_output>"
159
- ],
160
- "bos_token": "<|endoftext|>",
161
  "clean_up_tokenization_spaces": false,
162
- "eos_token": "<|endoftext|>",
 
163
  "extra_special_tokens": {},
164
- "model_max_length": 8192,
165
- "pad_token": "<|endoftext|>",
166
  "tokenizer_class": "GPT2Tokenizer",
167
- "unk_token": "<|endoftext|>",
168
- "vocab_size": 49152
169
  }
 
1
  {
2
+ "add_bos_token": true,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
 
 
 
 
 
 
 
 
5
  "1": {
6
+ "content": "<pad>",
7
  "lstrip": false,
8
+ "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
  "2": {
14
+ "content": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "lstrip": false,
16
+ "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  }
21
  },
22
+ "bos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "clean_up_tokenization_spaces": false,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
  "extra_special_tokens": {},
27
+ "model_max_length": 1000000000000000019884624838656,
28
+ "pad_token": "</s>",
29
  "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "</s>"
 
31
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff