Delete files t o k e n i z e r _ c o n f i g _ b k . j s o n with huggingface_hub
Browse files- tokenizer_config_bk.json +0 -304
tokenizer_config_bk.json
DELETED
|
@@ -1,304 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": null,
|
| 5 |
-
"added_tokens_decoder": {
|
| 6 |
-
"0": {
|
| 7 |
-
"content": "<unk>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": true,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"1": {
|
| 15 |
-
"content": "<s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": false
|
| 21 |
-
},
|
| 22 |
-
"2": {
|
| 23 |
-
"content": "<|endoftext|>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": true,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": true
|
| 29 |
-
},
|
| 30 |
-
"32000": {
|
| 31 |
-
"content": "<fim_prefix>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false,
|
| 36 |
-
"special": true
|
| 37 |
-
},
|
| 38 |
-
"32001": {
|
| 39 |
-
"content": "<fim_middle>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": false,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false,
|
| 44 |
-
"special": true
|
| 45 |
-
},
|
| 46 |
-
"32002": {
|
| 47 |
-
"content": "<fim_suffix>",
|
| 48 |
-
"lstrip": false,
|
| 49 |
-
"normalized": false,
|
| 50 |
-
"rstrip": false,
|
| 51 |
-
"single_word": false,
|
| 52 |
-
"special": true
|
| 53 |
-
},
|
| 54 |
-
"32003": {
|
| 55 |
-
"content": "<fim_pad>",
|
| 56 |
-
"lstrip": false,
|
| 57 |
-
"normalized": false,
|
| 58 |
-
"rstrip": false,
|
| 59 |
-
"single_word": false,
|
| 60 |
-
"special": true
|
| 61 |
-
},
|
| 62 |
-
"32004": {
|
| 63 |
-
"content": "<filename>",
|
| 64 |
-
"lstrip": false,
|
| 65 |
-
"normalized": false,
|
| 66 |
-
"rstrip": false,
|
| 67 |
-
"single_word": false,
|
| 68 |
-
"special": true
|
| 69 |
-
},
|
| 70 |
-
"32005": {
|
| 71 |
-
"content": "<gh_stars>",
|
| 72 |
-
"lstrip": false,
|
| 73 |
-
"normalized": false,
|
| 74 |
-
"rstrip": false,
|
| 75 |
-
"single_word": false,
|
| 76 |
-
"special": true
|
| 77 |
-
},
|
| 78 |
-
"32006": {
|
| 79 |
-
"content": "<issue_start>",
|
| 80 |
-
"lstrip": false,
|
| 81 |
-
"normalized": false,
|
| 82 |
-
"rstrip": false,
|
| 83 |
-
"single_word": false,
|
| 84 |
-
"special": true
|
| 85 |
-
},
|
| 86 |
-
"32007": {
|
| 87 |
-
"content": "<issue_comment>",
|
| 88 |
-
"lstrip": false,
|
| 89 |
-
"normalized": false,
|
| 90 |
-
"rstrip": false,
|
| 91 |
-
"single_word": false,
|
| 92 |
-
"special": true
|
| 93 |
-
},
|
| 94 |
-
"32008": {
|
| 95 |
-
"content": "<issue_closed>",
|
| 96 |
-
"lstrip": false,
|
| 97 |
-
"normalized": false,
|
| 98 |
-
"rstrip": false,
|
| 99 |
-
"single_word": false,
|
| 100 |
-
"special": true
|
| 101 |
-
},
|
| 102 |
-
"32009": {
|
| 103 |
-
"content": "<jupyter_start>",
|
| 104 |
-
"lstrip": false,
|
| 105 |
-
"normalized": false,
|
| 106 |
-
"rstrip": false,
|
| 107 |
-
"single_word": false,
|
| 108 |
-
"special": true
|
| 109 |
-
},
|
| 110 |
-
"32010": {
|
| 111 |
-
"content": "<jupyter_text>",
|
| 112 |
-
"lstrip": false,
|
| 113 |
-
"normalized": false,
|
| 114 |
-
"rstrip": false,
|
| 115 |
-
"single_word": false,
|
| 116 |
-
"special": true
|
| 117 |
-
},
|
| 118 |
-
"32011": {
|
| 119 |
-
"content": "<jupyter_code>",
|
| 120 |
-
"lstrip": false,
|
| 121 |
-
"normalized": false,
|
| 122 |
-
"rstrip": false,
|
| 123 |
-
"single_word": false,
|
| 124 |
-
"special": true
|
| 125 |
-
},
|
| 126 |
-
"32012": {
|
| 127 |
-
"content": "<jupyter_output>",
|
| 128 |
-
"lstrip": false,
|
| 129 |
-
"normalized": false,
|
| 130 |
-
"rstrip": false,
|
| 131 |
-
"single_word": false,
|
| 132 |
-
"special": true
|
| 133 |
-
},
|
| 134 |
-
"32013": {
|
| 135 |
-
"content": "<empty_output>",
|
| 136 |
-
"lstrip": false,
|
| 137 |
-
"normalized": false,
|
| 138 |
-
"rstrip": false,
|
| 139 |
-
"single_word": false,
|
| 140 |
-
"special": true
|
| 141 |
-
},
|
| 142 |
-
"32014": {
|
| 143 |
-
"content": "<commit_before>",
|
| 144 |
-
"lstrip": false,
|
| 145 |
-
"normalized": false,
|
| 146 |
-
"rstrip": false,
|
| 147 |
-
"single_word": false,
|
| 148 |
-
"special": true
|
| 149 |
-
},
|
| 150 |
-
"32015": {
|
| 151 |
-
"content": "<commit_msg>",
|
| 152 |
-
"lstrip": false,
|
| 153 |
-
"normalized": false,
|
| 154 |
-
"rstrip": false,
|
| 155 |
-
"single_word": false,
|
| 156 |
-
"special": true
|
| 157 |
-
},
|
| 158 |
-
"32016": {
|
| 159 |
-
"content": "<commit_after>",
|
| 160 |
-
"lstrip": false,
|
| 161 |
-
"normalized": false,
|
| 162 |
-
"rstrip": false,
|
| 163 |
-
"single_word": false,
|
| 164 |
-
"special": true
|
| 165 |
-
},
|
| 166 |
-
"32017": {
|
| 167 |
-
"content": "<reponame>",
|
| 168 |
-
"lstrip": false,
|
| 169 |
-
"normalized": false,
|
| 170 |
-
"rstrip": false,
|
| 171 |
-
"single_word": false,
|
| 172 |
-
"special": true
|
| 173 |
-
},
|
| 174 |
-
"32018": {
|
| 175 |
-
"content": "<tool_response>",
|
| 176 |
-
"lstrip": false,
|
| 177 |
-
"normalized": false,
|
| 178 |
-
"rstrip": false,
|
| 179 |
-
"single_word": false,
|
| 180 |
-
"special": true
|
| 181 |
-
},
|
| 182 |
-
"32019": {
|
| 183 |
-
"content": "<tool_call>",
|
| 184 |
-
"lstrip": false,
|
| 185 |
-
"normalized": false,
|
| 186 |
-
"rstrip": false,
|
| 187 |
-
"single_word": false,
|
| 188 |
-
"special": true
|
| 189 |
-
},
|
| 190 |
-
"32020": {
|
| 191 |
-
"content": "<tools>",
|
| 192 |
-
"lstrip": false,
|
| 193 |
-
"normalized": false,
|
| 194 |
-
"rstrip": false,
|
| 195 |
-
"single_word": false,
|
| 196 |
-
"special": true
|
| 197 |
-
},
|
| 198 |
-
"32021": {
|
| 199 |
-
"content": "</tool_response>",
|
| 200 |
-
"lstrip": false,
|
| 201 |
-
"normalized": false,
|
| 202 |
-
"rstrip": false,
|
| 203 |
-
"single_word": false,
|
| 204 |
-
"special": true
|
| 205 |
-
},
|
| 206 |
-
"32022": {
|
| 207 |
-
"content": "</tool_call>",
|
| 208 |
-
"lstrip": false,
|
| 209 |
-
"normalized": false,
|
| 210 |
-
"rstrip": false,
|
| 211 |
-
"single_word": false,
|
| 212 |
-
"special": true
|
| 213 |
-
},
|
| 214 |
-
"32023": {
|
| 215 |
-
"content": "</tools>",
|
| 216 |
-
"lstrip": false,
|
| 217 |
-
"normalized": false,
|
| 218 |
-
"rstrip": false,
|
| 219 |
-
"single_word": false,
|
| 220 |
-
"special": true
|
| 221 |
-
},
|
| 222 |
-
"32024": {
|
| 223 |
-
"content": "<|endofsystemprompt|>",
|
| 224 |
-
"lstrip": false,
|
| 225 |
-
"normalized": false,
|
| 226 |
-
"rstrip": false,
|
| 227 |
-
"single_word": false,
|
| 228 |
-
"special": true
|
| 229 |
-
},
|
| 230 |
-
"32025": {
|
| 231 |
-
"content": "<|beginofsystem|>",
|
| 232 |
-
"lstrip": false,
|
| 233 |
-
"normalized": false,
|
| 234 |
-
"rstrip": false,
|
| 235 |
-
"single_word": false,
|
| 236 |
-
"special": true
|
| 237 |
-
},
|
| 238 |
-
"32026": {
|
| 239 |
-
"content": "<|beginofuser|>",
|
| 240 |
-
"lstrip": false,
|
| 241 |
-
"normalized": false,
|
| 242 |
-
"rstrip": false,
|
| 243 |
-
"single_word": false,
|
| 244 |
-
"special": true
|
| 245 |
-
},
|
| 246 |
-
"32027": {
|
| 247 |
-
"content": "<|endofchat|>",
|
| 248 |
-
"lstrip": false,
|
| 249 |
-
"normalized": false,
|
| 250 |
-
"rstrip": false,
|
| 251 |
-
"single_word": false,
|
| 252 |
-
"special": true
|
| 253 |
-
}
|
| 254 |
-
},
|
| 255 |
-
"additional_special_tokens": [
|
| 256 |
-
"<fim_prefix>",
|
| 257 |
-
"<fim_middle>",
|
| 258 |
-
"<fim_suffix>",
|
| 259 |
-
"<fim_pad>",
|
| 260 |
-
"<filename>",
|
| 261 |
-
"<gh_stars>",
|
| 262 |
-
"<issue_start>",
|
| 263 |
-
"<issue_comment>",
|
| 264 |
-
"<issue_closed>",
|
| 265 |
-
"<jupyter_start>",
|
| 266 |
-
"<jupyter_text>",
|
| 267 |
-
"<jupyter_code>",
|
| 268 |
-
"<jupyter_output>",
|
| 269 |
-
"<empty_output>",
|
| 270 |
-
"<commit_before>",
|
| 271 |
-
"<commit_msg>",
|
| 272 |
-
"<commit_after>",
|
| 273 |
-
"<reponame>",
|
| 274 |
-
"<tool_call>",
|
| 275 |
-
"<tool_response>",
|
| 276 |
-
"<tools>",
|
| 277 |
-
"</tool_call>",
|
| 278 |
-
"</tool_response>",
|
| 279 |
-
"</tools>",
|
| 280 |
-
"<|endofsystemprompt|>",
|
| 281 |
-
"<|beginofsystem|>",
|
| 282 |
-
"<|beginofuser|>",
|
| 283 |
-
"<|endofchat|>"
|
| 284 |
-
],
|
| 285 |
-
"bos_token": "<|endoftext|>",
|
| 286 |
-
"chat_template": [
|
| 287 |
-
{
|
| 288 |
-
"name": "default",
|
| 289 |
-
"template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|beginofuser|>' + message['content'] }}{% elif message['role'] == 'system' %}{{ message['content'] + '<|endofsystemprompt|>' }}{% elif message['role'] == 'assistant' %}{{ '<|beginofsystem|>' + message['content'] }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|beginofsystem|>' }}{% endif %}{% endfor %}" },
|
| 290 |
-
{
|
| 291 |
-
"name": "tool_use",
|
| 292 |
-
"template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": ' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\\n\\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\\n Returns:\\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}, \"name\": {\"title\": \"Name\", \"type\": \"string\"}}, \"required\": [\"arguments\", \"name\"], \"title\": \"FunctionCall\", \"type\": \"object\"}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"arguments\": <args-dict>, \"name\": <function-name>}\n' }}\n{{- '</tool_call><|endofsystemprompt|>' }}\n{%- for message in messages %}{%- if message.role == \"user\" %}{{- '<|beginofuser|>' + message.content }}{%- if message.role == \"assistant\" and message.tool_calls is not defined) %} {{- '<|beginofsystem|>' + message.content }}{%- elif message.role == \"assistant\" %}{{- '<tool_call>\n' }}{%- for tool_call in message.tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}{{- '{ ' }}{%- if tool_call.arguments is defined %}{{- '\"arguments\": ' }}{{- tool_call.arguments|tojson }}{{- ', '}}{%- endif %}{{- '\"name\": \"' }}{{- tool_call.name }}{{- '\"}' }}{{- '\n</tool_call> ' }}\n {%- endfor %}{%- elif message.role == \"tool\" %}{%- if not message.name is defined %}{{- raise_exception(\"Tool response dicts require a 'name' key indicating the name of the called function!\") }}{%- endif %}{{- '<tool_response>\n' }}{{- '{\"name\": \"' }}{{- message.name }}{{- '\", \"content\": ' }}{{- message.content|tojson + '}' }}{{- '\n</tool_response>\n' }}{%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}{{- '<|beginofsystem|>' }}{%- endif %}\n"
|
| 293 |
-
}
|
| 294 |
-
],
|
| 295 |
-
"clean_up_tokenization_spaces": false,
|
| 296 |
-
"eos_token": "<|endoftext|>",
|
| 297 |
-
"legacy": true,
|
| 298 |
-
"model_max_length": 8192,
|
| 299 |
-
"pad_token": null,
|
| 300 |
-
"sp_model_kwargs": {},
|
| 301 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 302 |
-
"unk_token": "<unk>",
|
| 303 |
-
"use_default_system_prompt": false
|
| 304 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|