toilaluan commited on
Commit
b5fca7c
·
verified ·
1 Parent(s): ed37a3d

Upload tokenizer

Browse files
added_tokens.json CHANGED
@@ -1,25 +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
- "<|pad|>": 151665,
18
- "<|quad_end|>": 151651,
19
- "<|quad_start|>": 151650,
20
- "<|repo_name|>": 151663,
21
- "<|video_pad|>": 151656,
22
- "<|vision_end|>": 151653,
23
- "<|vision_pad|>": 151654,
24
- "<|vision_start|>": 151652
25
  }
 
1
  {
2
+ "<|pad|>": 49152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,19 +1,30 @@
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": "<|endoftext|>",
19
  "lstrip": false,
@@ -27,5 +38,12 @@
27
  "normalized": false,
28
  "rstrip": false,
29
  "single_word": false
 
 
 
 
 
 
 
30
  }
31
  }
 
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,
 
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false
41
+ },
42
+ "unk_token": {
43
+ "content": "<|endoftext|>",
44
+ "lstrip": false,
45
+ "normalized": false,
46
+ "rstrip": false,
47
+ "single_word": false
48
  }
49
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:027dcce00fe86b1c2195ddb98004030df12a9a4334e7df1471d1df6536bb922d
3
- size 11422080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e11895892b4d437855b1b0abc56ef73cb5b67ee15624c9cff021a54a23d30106
3
+ size 3522839
tokenizer_config.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
- "151643": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
  "normalized": false,
@@ -10,7 +9,7 @@
10
  "single_word": false,
11
  "special": true
12
  },
13
- "151644": {
14
  "content": "<|im_start|>",
15
  "lstrip": false,
16
  "normalized": false,
@@ -18,7 +17,7 @@
18
  "single_word": false,
19
  "special": true
20
  },
21
- "151645": {
22
  "content": "<|im_end|>",
23
  "lstrip": false,
24
  "normalized": false,
@@ -26,159 +25,119 @@
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
- "151665": {
182
  "content": "<|pad|>",
183
  "lstrip": false,
184
  "normalized": false,
@@ -188,29 +147,31 @@
188
  }
189
  },
190
  "additional_special_tokens": [
 
191
  "<|im_start|>",
192
  "<|im_end|>",
193
- "<|object_ref_start|>",
194
- "<|object_ref_end|>",
195
- "<|box_start|>",
196
- "<|box_end|>",
197
- "<|quad_start|>",
198
- "<|quad_end|>",
199
- "<|vision_start|>",
200
- "<|vision_end|>",
201
- "<|vision_pad|>",
202
- "<|image_pad|>",
203
- "<|video_pad|>"
 
 
 
204
  ],
205
- "bos_token": null,
206
- "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
207
  "clean_up_tokenization_spaces": false,
208
  "eos_token": "<|endoftext|>",
209
- "errors": "replace",
210
  "extra_special_tokens": {},
211
- "model_max_length": 32768,
212
  "pad_token": "<|pad|>",
213
- "split_special_tokens": false,
214
- "tokenizer_class": "Qwen2Tokenizer",
215
- "unk_token": null
216
  }
 
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "0": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
 
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "1": {
13
  "content": "<|im_start|>",
14
  "lstrip": false,
15
  "normalized": false,
 
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "2": {
21
  "content": "<|im_end|>",
22
  "lstrip": false,
23
  "normalized": 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
+ "49152": {
141
  "content": "<|pad|>",
142
  "lstrip": false,
143
  "normalized": false,
 
147
  }
148
  },
149
  "additional_special_tokens": [
150
+ "<|endoftext|>",
151
  "<|im_start|>",
152
  "<|im_end|>",
153
+ "<repo_name>",
154
+ "<reponame>",
155
+ "<file_sep>",
156
+ "<filename>",
157
+ "<gh_stars>",
158
+ "<issue_start>",
159
+ "<issue_comment>",
160
+ "<issue_closed>",
161
+ "<jupyter_start>",
162
+ "<jupyter_text>",
163
+ "<jupyter_code>",
164
+ "<jupyter_output>",
165
+ "<jupyter_script>",
166
+ "<empty_output>"
167
  ],
168
+ "bos_token": "<|endoftext|>",
 
169
  "clean_up_tokenization_spaces": false,
170
  "eos_token": "<|endoftext|>",
 
171
  "extra_special_tokens": {},
172
+ "model_max_length": 1000000000000000019884624838656,
173
  "pad_token": "<|pad|>",
174
+ "tokenizer_class": "GPT2Tokenizer",
175
+ "unk_token": "<|endoftext|>",
176
+ "vocab_size": 49152
177
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff