Delete tokenizer_config.json
Browse files- tokenizer_config.json +0 -194
tokenizer_config.json
DELETED
@@ -1,194 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": null,
|
5 |
-
"added_tokens_decoder": {
|
6 |
-
"151643": {
|
7 |
-
"content": "<|end▁of▁sentence|>",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false,
|
12 |
-
"special": true
|
13 |
-
},
|
14 |
-
"151644": {
|
15 |
-
"content": "<|User|>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false,
|
20 |
-
"special": false
|
21 |
-
},
|
22 |
-
"151645": {
|
23 |
-
"content": "<|Assistant|>",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": false,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false,
|
28 |
-
"special": false
|
29 |
-
},
|
30 |
-
"151646": {
|
31 |
-
"content": "<|begin▁of▁sentence|>",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": true
|
37 |
-
},
|
38 |
-
"151647": {
|
39 |
-
"content": "<|EOT|>",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false,
|
44 |
-
"special": false
|
45 |
-
},
|
46 |
-
"151648": {
|
47 |
-
"content": "<think>",
|
48 |
-
"lstrip": false,
|
49 |
-
"normalized": false,
|
50 |
-
"rstrip": false,
|
51 |
-
"single_word": false,
|
52 |
-
"special": false
|
53 |
-
},
|
54 |
-
"151649": {
|
55 |
-
"content": "</think>",
|
56 |
-
"lstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"rstrip": false,
|
59 |
-
"single_word": false,
|
60 |
-
"special": false
|
61 |
-
},
|
62 |
-
"151650": {
|
63 |
-
"content": "<|quad_start|>",
|
64 |
-
"lstrip": false,
|
65 |
-
"normalized": false,
|
66 |
-
"rstrip": false,
|
67 |
-
"single_word": false,
|
68 |
-
"special": true
|
69 |
-
},
|
70 |
-
"151651": {
|
71 |
-
"content": "<|quad_end|>",
|
72 |
-
"lstrip": false,
|
73 |
-
"normalized": false,
|
74 |
-
"rstrip": false,
|
75 |
-
"single_word": false,
|
76 |
-
"special": true
|
77 |
-
},
|
78 |
-
"151652": {
|
79 |
-
"content": "<|vision_start|>",
|
80 |
-
"lstrip": false,
|
81 |
-
"normalized": false,
|
82 |
-
"rstrip": false,
|
83 |
-
"single_word": false,
|
84 |
-
"special": true
|
85 |
-
},
|
86 |
-
"151653": {
|
87 |
-
"content": "<|vision_end|>",
|
88 |
-
"lstrip": false,
|
89 |
-
"normalized": false,
|
90 |
-
"rstrip": false,
|
91 |
-
"single_word": false,
|
92 |
-
"special": true
|
93 |
-
},
|
94 |
-
"151654": {
|
95 |
-
"content": "<|vision_pad|>",
|
96 |
-
"lstrip": false,
|
97 |
-
"normalized": false,
|
98 |
-
"rstrip": false,
|
99 |
-
"single_word": false,
|
100 |
-
"special": true
|
101 |
-
},
|
102 |
-
"151655": {
|
103 |
-
"content": "<|image_pad|>",
|
104 |
-
"lstrip": false,
|
105 |
-
"normalized": false,
|
106 |
-
"rstrip": false,
|
107 |
-
"single_word": false,
|
108 |
-
"special": true
|
109 |
-
},
|
110 |
-
"151656": {
|
111 |
-
"content": "<|video_pad|>",
|
112 |
-
"lstrip": false,
|
113 |
-
"normalized": false,
|
114 |
-
"rstrip": false,
|
115 |
-
"single_word": false,
|
116 |
-
"special": true
|
117 |
-
},
|
118 |
-
"151657": {
|
119 |
-
"content": "<tool_call>",
|
120 |
-
"lstrip": false,
|
121 |
-
"normalized": false,
|
122 |
-
"rstrip": false,
|
123 |
-
"single_word": false,
|
124 |
-
"special": false
|
125 |
-
},
|
126 |
-
"151658": {
|
127 |
-
"content": "</tool_call>",
|
128 |
-
"lstrip": false,
|
129 |
-
"normalized": false,
|
130 |
-
"rstrip": false,
|
131 |
-
"single_word": false,
|
132 |
-
"special": false
|
133 |
-
},
|
134 |
-
"151659": {
|
135 |
-
"content": "<|fim_prefix|>",
|
136 |
-
"lstrip": false,
|
137 |
-
"normalized": false,
|
138 |
-
"rstrip": false,
|
139 |
-
"single_word": false,
|
140 |
-
"special": false
|
141 |
-
},
|
142 |
-
"151660": {
|
143 |
-
"content": "<|fim_middle|>",
|
144 |
-
"lstrip": false,
|
145 |
-
"normalized": false,
|
146 |
-
"rstrip": false,
|
147 |
-
"single_word": false,
|
148 |
-
"special": false
|
149 |
-
},
|
150 |
-
"151661": {
|
151 |
-
"content": "<|fim_suffix|>",
|
152 |
-
"lstrip": false,
|
153 |
-
"normalized": false,
|
154 |
-
"rstrip": false,
|
155 |
-
"single_word": false,
|
156 |
-
"special": false
|
157 |
-
},
|
158 |
-
"151662": {
|
159 |
-
"content": "<|fim_pad|>",
|
160 |
-
"lstrip": false,
|
161 |
-
"normalized": false,
|
162 |
-
"rstrip": false,
|
163 |
-
"single_word": false,
|
164 |
-
"special": false
|
165 |
-
},
|
166 |
-
"151663": {
|
167 |
-
"content": "<|repo_name|>",
|
168 |
-
"lstrip": false,
|
169 |
-
"normalized": false,
|
170 |
-
"rstrip": false,
|
171 |
-
"single_word": false,
|
172 |
-
"special": false
|
173 |
-
},
|
174 |
-
"151664": {
|
175 |
-
"content": "<|file_sep|>",
|
176 |
-
"lstrip": false,
|
177 |
-
"normalized": false,
|
178 |
-
"rstrip": false,
|
179 |
-
"single_word": false,
|
180 |
-
"special": false
|
181 |
-
}
|
182 |
-
},
|
183 |
-
"bos_token": "<|begin▁of▁sentence|>",
|
184 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}",
|
185 |
-
"clean_up_tokenization_spaces": false,
|
186 |
-
"eos_token": "<|end▁of▁sentence|>",
|
187 |
-
"legacy": true,
|
188 |
-
"model_max_length": 16384,
|
189 |
-
"pad_token": "<|end▁of▁sentence|>",
|
190 |
-
"sp_model_kwargs": {},
|
191 |
-
"tokenizer_class": "LlamaTokenizer",
|
192 |
-
"unk_token": null,
|
193 |
-
"use_default_system_prompt": false
|
194 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|