Hugging Face's logo

trychoosing
/
hugcoder

Model card Files
xet
 Community
trychoosing commited on
Commit
e61679a
·
verified ·
1 Parent(s): 9c840c5

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +3 -24
  2. tokenizer.json +0 -0
  3. tokenizer.model +3 -0
  4. tokenizer_config.json +15 -158
special_tokens_map.json CHANGED
@@ -1,41 +1,20 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|endoftext|>",
4
- "<fim_prefix>",
5
- "<fim_middle>",
6
- "<fim_suffix>",
7
- "<fim_pad>",
8
- "<filename>",
9
- "<gh_stars>",
10
- "<issue_start>",
11
- "<issue_comment>",
12
- "<issue_closed>",
13
- "<jupyter_start>",
14
- "<jupyter_text>",
15
- "<jupyter_code>",
16
- "<jupyter_output>",
17
- "<empty_output>",
18
- "<commit_before>",
19
- "<commit_msg>",
20
- "<commit_after>",
21
- "<reponame>"
22
- ],
23
  "bos_token": {
24
- "content": "<|endoftext|>",
25
  "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "eos_token": {
31
- "content": "<|endoftext|>",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
35
  "single_word": false
36
  },
37
  "unk_token": {
38
- "content": "<|endoftext|>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
+ "content": "<s>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "</s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "unk_token": {
17
+ "content": "<unk>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,8 +1,10 @@
1
  {
2
- "add_prefix_space": false,
 
 
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
@@ -10,7 +12,7 @@
10
  "special": true
11
  },
12
  "1": {
13
- "content": "<fim_prefix>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
@@ -18,135 +20,7 @@
18
  "special": true
19
  },
20
  "2": {
21
- "content": "<fim_middle>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<fim_suffix>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<fim_pad>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<filename>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "6": {
53
- "content": "<gh_stars>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "7": {
61
- "content": "<issue_start>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "8": {
69
- "content": "<issue_comment>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "9": {
77
- "content": "<issue_closed>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "10": {
85
- "content": "<jupyter_start>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "11": {
93
- "content": "<jupyter_text>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "12": {
101
- "content": "<jupyter_code>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "13": {
109
- "content": "<jupyter_output>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "14": {
117
- "content": "<empty_output>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "15": {
125
- "content": "<commit_before>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "16": {
133
- "content": "<commit_msg>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "17": {
141
- "content": "<commit_after>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "18": {
149
- "content": "<reponame>",
150
  "lstrip": false,
151
  "normalized": false,
152
  "rstrip": false,
@@ -154,33 +28,16 @@
154
  "special": true
155
  }
156
  },
157
- "additional_special_tokens": [
158
- "<|endoftext|>",
159
- "<fim_prefix>",
160
- "<fim_middle>",
161
- "<fim_suffix>",
162
- "<fim_pad>",
163
- "<filename>",
164
- "<gh_stars>",
165
- "<issue_start>",
166
- "<issue_comment>",
167
- "<issue_closed>",
168
- "<jupyter_start>",
169
- "<jupyter_text>",
170
- "<jupyter_code>",
171
- "<jupyter_output>",
172
- "<empty_output>",
173
- "<commit_before>",
174
- "<commit_msg>",
175
- "<commit_after>",
176
- "<reponame>"
177
- ],
178
- "bos_token": "<|endoftext|>",
179
  "clean_up_tokenization_spaces": false,
180
- "eos_token": "<|endoftext|>",
181
  "extra_special_tokens": {},
 
182
  "model_max_length": 1000000000000000019884624838656,
183
- "tokenizer_class": "GPT2Tokenizer",
184
- "unk_token": "<|endoftext|>",
185
- "vocab_size": 50000
 
 
 
186
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
+ "content": "<unk>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
 
12
  "special": true
13
  },
14
  "1": {
15
+ "content": "<s>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
 
20
  "special": true
21
  },
22
  "2": {
23
+ "content": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  "lstrip": false,
25
  "normalized": false,
26
  "rstrip": false,
 
28
  "special": true
29
  }
30
  },
31
+ "bos_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
  "extra_special_tokens": {},
35
+ "legacy": true,
36
  "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
  }