Hugging Face's logo

rtl-llm
/
qwen2.5coder-7b-origen-all-shuffled

Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
Model card Files
xet
Community
charleshong3 commited on
Commit
e5a2eeb
·
verified ·
1 Parent(s): 64dabd2

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +1 -22
  2. special_tokens_map.json +8 -16
  3. tokenizer.json +2 -2
  4. tokenizer_config.json +3 -188
added_tokens.json CHANGED
@@ -1,24 +1,3 @@
1
  {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|box_end|>": 151649,
5
- "<|box_start|>": 151648,
6
- "<|endoftext|>": 151643,
7
- "<|file_sep|>": 151664,
8
- "<|fim_middle|>": 151660,
9
- "<|fim_pad|>": 151662,
10
- "<|fim_prefix|>": 151659,
11
- "<|fim_suffix|>": 151661,
12
- "<|im_end|>": 151645,
13
- "<|im_start|>": 151644,
14
- "<|image_pad|>": 151655,
15
- "<|object_ref_end|>": 151647,
16
- "<|object_ref_start|>": 151646,
17
- "<|quad_end|>": 151651,
18
- "<|quad_start|>": 151650,
19
- "<|repo_name|>": 151663,
20
- "<|video_pad|>": 151656,
21
- "<|vision_end|>": 151653,
22
- "<|vision_pad|>": 151654,
23
- "<|vision_start|>": 151652
24
  }
 
1
  {
2
+ "<|endoftext|>": 151643
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  }
special_tokens_map.json CHANGED
@@ -1,21 +1,6 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
  "eos_token": {
18
- "content": "<|im_end|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
@@ -27,5 +12,12 @@
27
  "normalized": false,
28
  "rstrip": false,
29
  "single_word": false
 
 
 
 
 
 
 
30
  }
31
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "eos_token": {
3
+ "content": "<|endoftext|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
 
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
  }
23
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c3c6d1699d808eea431043c5d9db4e6c191698789c69a5d35f11aeabc2304a
3
+ size 11417884
tokenizer_config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "151643": {
6
  "content": "<|endoftext|>",
@@ -9,200 +7,17 @@
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
  }
181
  },
182
- "additional_special_tokens": [
183
- "<|im_start|>",
184
- "<|im_end|>",
185
- "<|object_ref_start|>",
186
- "<|object_ref_end|>",
187
- "<|box_start|>",
188
- "<|box_end|>",
189
- "<|quad_start|>",
190
- "<|quad_end|>",
191
- "<|vision_start|>",
192
- "<|vision_end|>",
193
- "<|vision_pad|>",
194
- "<|image_pad|>",
195
- "<|video_pad|>"
196
- ],
197
  "bos_token": null,
198
  "clean_up_tokenization_spaces": false,
199
- "eos_token": "<|im_end|>",
200
  "errors": "replace",
201
  "extra_special_tokens": {},
202
  "fast_tokenizer": true,
203
- "model_max_length": 32768,
204
  "pad_token": "<|endoftext|>",
205
  "split_special_tokens": false,
206
  "tokenizer_class": "Qwen2Tokenizer",
207
- "unk_token": null
208
  }
 
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "151643": {
4
  "content": "<|endoftext|>",
 
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  }
11
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "bos_token": null,
13
  "clean_up_tokenization_spaces": false,
14
+ "eos_token": "<|endoftext|>",
15
  "errors": "replace",
16
  "extra_special_tokens": {},
17
  "fast_tokenizer": true,
18
+ "model_max_length": 1000000000000000019884624838656,
19
  "pad_token": "<|endoftext|>",
20
  "split_special_tokens": false,
21
  "tokenizer_class": "Qwen2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
  }