Hugging Face's logo

Arko007
/
zenyx-v2-tokenizer

Text Generation
Transformers
English
tokenizer
bpe
byte-level-bpe
zenyx
reasoning
math
code
conversational
Model card Files
xet
 Community
Arko007 commited on
Commit
acb664b
·
verified ·
1 Parent(s): 15e9937

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +115 -10
  2. tokenizer.json +81 -0
  3. tokenizer_config.json +136 -22
special_tokens_map.json CHANGED
@@ -1,12 +1,117 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|unk|>",
5
- "pad_token": "<|pad|>",
6
  "additional_special_tokens": [
7
- "<think>",
8
- "</think>",
9
- "<scratchpad>",
10
- "<verify>"
11
- ]
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
 
 
 
 
2
  "additional_special_tokens": [
3
+ {
4
+ "content": "<think>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</think>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<scratchpad>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<verify>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|im_start|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<tool_call>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</tool_call>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<tool_response>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</tool_response>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<|fim_prefix|>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<|fim_suffix|>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<|fim_middle|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ }
94
+ ],
95
+ "bos_token": {
96
+ "content": "<|endoftext|>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false
101
+ },
102
+ "eos_token": "<|im_end|>",
103
+ "pad_token": {
104
+ "content": "<|pad|>",
105
+ "lstrip": false,
106
+ "normalized": false,
107
+ "rstrip": false,
108
+ "single_word": false
109
+ },
110
+ "unk_token": {
111
+ "content": "<|unk|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false
116
+ }
117
+ }
tokenizer.json CHANGED
@@ -65,6 +65,87 @@
65
  "rstrip": false,
66
  "normalized": false,
67
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "normalizer": null,
 
65
  "rstrip": false,
66
  "normalized": false,
67
  "special": true
68
+ },
69
+ {
70
+ "id": 32768,
71
+ "content": "<|im_start|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 32769,
80
+ "content": "<|im_end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 32770,
89
+ "content": "<tool_call>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 32771,
98
+ "content": "</tool_call>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 32772,
107
+ "content": "<tool_response>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 32773,
116
+ "content": "</tool_response>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 32774,
125
+ "content": "<|fim_prefix|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 32775,
134
+ "content": "<|fim_suffix|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 32776,
143
+ "content": "<|fim_middle|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
  }
150
  ],
151
  "normalizer": null,
tokenizer_config.json CHANGED
@@ -1,44 +1,158 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|unk|>",
5
- "pad_token": "<|pad|>",
6
- "model_max_length": 131072,
7
- "tokenizer_class": "PreTrainedTokenizerFast",
8
- "vocab_size": 32768,
9
  "add_bos_token": false,
10
  "add_eos_token": false,
11
- "clean_up_tokenization_spaces": false,
12
- "additional_special_tokens": [
13
- "<think>",
14
- "</think>",
15
- "<scratchpad>",
16
- "<verify>"
17
- ],
18
  "added_tokens_decoder": {
19
  "0": {
20
  "content": "<|endoftext|>",
21
- "special": true,
22
  "lstrip": false,
 
23
  "rstrip": false,
24
  "single_word": false,
25
- "normalized": false
26
  },
27
  "1": {
28
  "content": "<|pad|>",
29
- "special": true,
30
  "lstrip": false,
 
31
  "rstrip": false,
32
  "single_word": false,
33
- "normalized": false
34
  },
35
  "2": {
36
  "content": "<|unk|>",
37
- "special": true,
38
  "lstrip": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  "rstrip": false,
40
  "single_word": false,
41
- "normalized": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
- }
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
 
 
 
 
 
 
 
2
  "add_bos_token": false,
3
  "add_eos_token": false,
 
 
 
 
 
 
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<|endoftext|>",
 
7
  "lstrip": false,
8
+ "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
+ "special": true
12
  },
13
  "1": {
14
  "content": "<|pad|>",
 
15
  "lstrip": false,
16
+ "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
+ "special": true
20
  },
21
  "2": {
22
  "content": "<|unk|>",
 
23
  "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<think>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "</think>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<scratchpad>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<verify>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32768": {
62
+ "content": "<|im_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32769": {
70
+ "content": "<|im_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32770": {
78
+ "content": "<tool_call>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32771": {
86
+ "content": "</tool_call>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32772": {
94
+ "content": "<tool_response>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
  "rstrip": false,
98
  "single_word": false,
99
+ "special": true
100
+ },
101
+ "32773": {
102
+ "content": "</tool_response>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32774": {
110
+ "content": "<|fim_prefix|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32775": {
118
+ "content": "<|fim_suffix|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32776": {
126
+ "content": "<|fim_middle|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
  }
133
+ },
134
+ "additional_special_tokens": [
135
+ "<think>",
136
+ "</think>",
137
+ "<scratchpad>",
138
+ "<verify>",
139
+ "<|im_start|>",
140
+ "<|im_end|>",
141
+ "<tool_call>",
142
+ "</tool_call>",
143
+ "<tool_response>",
144
+ "</tool_response>",
145
+ "<|fim_prefix|>",
146
+ "<|fim_suffix|>",
147
+ "<|fim_middle|>"
148
+ ],
149
+ "bos_token": "<|endoftext|>",
150
+ "clean_up_tokenization_spaces": false,
151
+ "eos_token": "<|im_end|>",
152
+ "extra_special_tokens": {},
153
+ "model_max_length": 131072,
154
+ "pad_token": "<|pad|>",
155
+ "tokenizer_class": "PreTrainedTokenizerFast",
156
+ "unk_token": "<|unk|>",
157
+ "vocab_size": 32768
158
+ }