Commit
•
6de1a96
1
Parent(s):
44aa18a
Upload tokenizer
Browse files- added_tokens.json +24 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +193 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32018,
|
| 3 |
+
"<|Assistant|>": 32020,
|
| 4 |
+
"<|EOT|>": 32021,
|
| 5 |
+
"<|User|>": 32019,
|
| 6 |
+
"<｜begin▁of▁sentence｜>": 32013,
|
| 7 |
+
"<｜end▁of▁sentence｜>": 32014,
|
| 8 |
+
"<｜fim▁begin｜>": 32016,
|
| 9 |
+
"<｜fim▁end｜>": 32017,
|
| 10 |
+
"<｜fim▁hole｜>": 32015,
|
| 11 |
+
"À": 32004,
|
| 12 |
+
"Á": 32002,
|
| 13 |
+
"õ": 32000,
|
| 14 |
+
"ö": 32011,
|
| 15 |
+
"÷": 32001,
|
| 16 |
+
"ø": 32006,
|
| 17 |
+
"ù": 32010,
|
| 18 |
+
"ú": 32007,
|
| 19 |
+
"û": 32012,
|
| 20 |
+
"ü": 32009,
|
| 21 |
+
"ý": 32003,
|
| 22 |
+
"þ": 32008,
|
| 23 |
+
"ÿ": 32005
|
| 24 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
| 3 |
+
size 500058
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"32000": {
|
| 6 |
+
"content": "õ",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": false
|
| 12 |
+
},
|
| 13 |
+
"32001": {
|
| 14 |
+
"content": "÷",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": false
|
| 20 |
+
},
|
| 21 |
+
"32002": {
|
| 22 |
+
"content": "Á",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32003": {
|
| 30 |
+
"content": "ý",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"32004": {
|
| 38 |
+
"content": "À",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"32005": {
|
| 46 |
+
"content": "ÿ",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"32006": {
|
| 54 |
+
"content": "ø",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"32007": {
|
| 62 |
+
"content": "ú",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"32008": {
|
| 70 |
+
"content": "þ",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"32009": {
|
| 78 |
+
"content": "ü",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"32010": {
|
| 86 |
+
"content": "ù",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"32011": {
|
| 94 |
+
"content": "ö",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"32012": {
|
| 102 |
+
"content": "û",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"32013": {
|
| 110 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"32014": {
|
| 118 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"32015": {
|
| 126 |
+
"content": "<｜fim▁hole｜>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"32016": {
|
| 134 |
+
"content": "<｜fim▁begin｜>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"32017": {
|
| 142 |
+
"content": "<｜fim▁end｜>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"32018": {
|
| 150 |
+
"content": "<pad>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"32019": {
|
| 158 |
+
"content": "<|User|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"32020": {
|
| 166 |
+
"content": "<|Assistant|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"32021": {
|
| 174 |
+
"content": "<|EOT|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 183 |
+
"chat_template": "{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] + '\\n\\n' }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'@@ Instruction\\n' + message['content'] + '\\n\\n'}}\n {%- else %}\n{{'@@ Response\\n' + message['content'] + '\\n' + eos_token + '\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}{% if add_generation_prompt %}{{ '@@ Response\n' }}{% endif %}",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 186 |
+
"legacy": true,
|
| 187 |
+
"model_max_length": 16384,
|
| 188 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 189 |
+
"sp_model_kwargs": {},
|
| 190 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 191 |
+
"unk_token": null,
|
| 192 |
+
"use_default_system_prompt": false
|
| 193 |
+
}
|