Hugging Face's logo

DEVECOAI
/
DeepSeek-Coder-V2-Lite-Instruct_r32_rsTrue

Transformers
Safetensors
Model card Files
xet
Community
pointt37 commited on
Commit
39b1e70
·
verified ·
1 Parent(s): 32d0e35

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +17 -17
  2. tokenizer_config.json +162 -162
special_tokens_map.json CHANGED
@@ -1,17 +1,17 @@
1
- {
2
- "bos_token": {
3
- "content": "<｜begin▁of▁sentence｜>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<｜end▁of▁sentence｜>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<｜end▁of▁sentence｜>"
17
- }
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<｜end▁of▁sentence｜>"
17
+ }
tokenizer_config.json CHANGED
@@ -1,162 +1,162 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "100000": {
7
- "content": "<｜begin▁of▁sentence｜>",
8
- "lstrip": false,
9
- "normalized": true,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "100001": {
15
- "content": "<｜end▁of▁sentence｜>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "100002": {
23
- "content": "<｜fim▁hole｜>",
24
- "lstrip": false,
25
- "normalized": true,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": false
29
- },
30
- "100003": {
31
- "content": "<｜fim▁begin｜>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false,
36
- "special": false
37
- },
38
- "100004": {
39
- "content": "<｜fim▁end｜>",
40
- "lstrip": false,
41
- "normalized": true,
42
- "rstrip": false,
43
- "single_word": false,
44
- "special": false
45
- },
46
- "100005": {
47
- "content": "<｜completion｜>",
48
- "lstrip": false,
49
- "normalized": true,
50
- "rstrip": false,
51
- "single_word": false,
52
- "special": false
53
- },
54
- "100006": {
55
- "content": "<｜User｜>",
56
- "lstrip": false,
57
- "normalized": true,
58
- "rstrip": false,
59
- "single_word": false,
60
- "special": false
61
- },
62
- "100007": {
63
- "content": "<｜Assistant｜>",
64
- "lstrip": false,
65
- "normalized": true,
66
- "rstrip": false,
67
- "single_word": false,
68
- "special": false
69
- },
70
- "100008": {
71
- "content": "<|EOT|>",
72
- "lstrip": false,
73
- "normalized": true,
74
- "rstrip": false,
75
- "single_word": false,
76
- "special": true
77
- },
78
- "100009": {
79
- "content": "<｜tool▁calls▁begin｜>",
80
- "lstrip": false,
81
- "normalized": true,
82
- "rstrip": false,
83
- "single_word": false,
84
- "special": false
85
- },
86
- "100010": {
87
- "content": "<｜tool▁calls▁end｜>",
88
- "lstrip": false,
89
- "normalized": true,
90
- "rstrip": false,
91
- "single_word": false,
92
- "special": false
93
- },
94
- "100011": {
95
- "content": "<｜tool▁call▁begin｜>",
96
- "lstrip": false,
97
- "normalized": true,
98
- "rstrip": false,
99
- "single_word": false,
100
- "special": false
101
- },
102
- "100012": {
103
- "content": "<｜tool▁call▁end｜>",
104
- "lstrip": false,
105
- "normalized": true,
106
- "rstrip": false,
107
- "single_word": false,
108
- "special": false
109
- },
110
- "100013": {
111
- "content": "<｜tool▁outputs▁begin｜>",
112
- "lstrip": false,
113
- "normalized": true,
114
- "rstrip": false,
115
- "single_word": false,
116
- "special": false
117
- },
118
- "100014": {
119
- "content": "<｜tool▁outputs▁end｜>",
120
- "lstrip": false,
121
- "normalized": true,
122
- "rstrip": false,
123
- "single_word": false,
124
- "special": false
125
- },
126
- "100015": {
127
- "content": "<｜tool▁output▁begin｜>",
128
- "lstrip": false,
129
- "normalized": true,
130
- "rstrip": false,
131
- "single_word": false,
132
- "special": false
133
- },
134
- "100016": {
135
- "content": "<｜tool▁output▁end｜>",
136
- "lstrip": false,
137
- "normalized": true,
138
- "rstrip": false,
139
- "single_word": false,
140
- "special": false
141
- },
142
- "100017": {
143
- "content": "<｜tool▁sep｜>",
144
- "lstrip": false,
145
- "normalized": true,
146
- "rstrip": false,
147
- "single_word": false,
148
- "special": false
149
- }
150
- },
151
- "bos_token": "<｜begin▁of▁sentence｜>",
152
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
153
- "clean_up_tokenization_spaces": false,
154
- "eos_token": "<｜end▁of▁sentence｜>",
155
- "legacy": true,
156
- "model_max_length": 16384,
157
- "pad_token": "<｜end▁of▁sentence｜>",
158
- "sp_model_kwargs": {},
159
- "tokenizer_class": "LlamaTokenizer",
160
- "unk_token": null,
161
- "use_default_system_prompt": false
162
- }
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "100000": {
7
+ "content": "<｜begin▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "100001": {
15
+ "content": "<｜end▁of▁sentence｜>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "100002": {
23
+ "content": "<｜fim▁hole｜>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "100003": {
31
+ "content": "<｜fim▁begin｜>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "100004": {
39
+ "content": "<｜fim▁end｜>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "100005": {
47
+ "content": "<｜completion｜>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "100006": {
55
+ "content": "<｜User｜>",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "100007": {
63
+ "content": "<｜Assistant｜>",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "100008": {
71
+ "content": "<|EOT|>",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "100009": {
79
+ "content": "<｜tool▁calls▁begin｜>",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "100010": {
87
+ "content": "<｜tool▁calls▁end｜>",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "100011": {
95
+ "content": "<｜tool▁call▁begin｜>",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "100012": {
103
+ "content": "<｜tool▁call▁end｜>",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "100013": {
111
+ "content": "<｜tool▁outputs▁begin｜>",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "100014": {
119
+ "content": "<｜tool▁outputs▁end｜>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "100015": {
127
+ "content": "<｜tool▁output▁begin｜>",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "100016": {
135
+ "content": "<｜tool▁output▁end｜>",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "100017": {
143
+ "content": "<｜tool▁sep｜>",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ }
150
+ },
151
+ "bos_token": "<｜begin▁of▁sentence｜>",
152
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
153
+ "clean_up_tokenization_spaces": false,
154
+ "eos_token": "<｜end▁of▁sentence｜>",
155
+ "legacy": true,
156
+ "model_max_length": 16384,
157
+ "pad_token": "<｜end▁of▁sentence｜>",
158
+ "sp_model_kwargs": {},
159
+ "tokenizer_class": "LlamaTokenizer",
160
+ "unk_token": null,
161
+ "use_default_system_prompt": false
162
+ }