Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +4 -29
- tokenizer.json +2 -2
- tokenizer_config.json +7 -194
- vocab.json +0 -0
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -1,31 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
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,
|
22 |
-
"single_word": false
|
23 |
-
},
|
24 |
-
"pad_token": {
|
25 |
-
"content": "<|endoftext|>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": false,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
}
|
31 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd34e1be1baf1dad8c9efbb4dd8f84b8ab74386af424da5cab8acfbf25c5123a
|
3 |
+
size 3557957
|
tokenizer_config.json
CHANGED
@@ -1,207 +1,20 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
"added_tokens_decoder": {
|
5 |
-
"
|
6 |
"content": "<|endoftext|>",
|
7 |
"lstrip": false,
|
8 |
-
"normalized":
|
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 |
-
"
|
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 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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",
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
-
"eos_token": "<|
|
201 |
-
"
|
202 |
-
"model_max_length": 131072,
|
203 |
"pad_token": "<|endoftext|>",
|
204 |
-
"
|
205 |
-
"
|
206 |
-
"unk_token": null
|
207 |
}
|
|
|
1 |
{
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
"content": "<|endoftext|>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
12 |
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"clean_up_tokenization_spaces": false,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
|
|
17 |
"pad_token": "<|endoftext|>",
|
18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
19 |
+
"unk_token": "<|endoftext|>"
|
|
|
20 |
}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|