File size: 13,209 Bytes
ce41e28 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 |
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<UNK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<CLS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<SEP>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<MASK_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<BOS_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<EOS_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<EOP_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"255000": {
"content": "<|START_OF_TURN_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255001": {
"content": "<|END_OF_TURN_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"255002": {
"content": "<|YES_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255003": {
"content": "<|NO_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255004": {
"content": "<|GOOD_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255005": {
"content": "<|BAD_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255006": {
"content": "<|USER_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255007": {
"content": "<|CHATBOT_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255008": {
"content": "<|SYSTEM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255009": {
"content": "<|USER_0_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255010": {
"content": "<|USER_1_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255011": {
"content": "<|USER_2_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255012": {
"content": "<|USER_3_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255013": {
"content": "<|USER_4_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255014": {
"content": "<|USER_5_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255015": {
"content": "<|USER_6_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255016": {
"content": "<|USER_7_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255017": {
"content": "<|USER_8_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255018": {
"content": "<|USER_9_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255019": {
"content": "<|START_THINKING|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255020": {
"content": "<|END_THINKING|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255021": {
"content": "<|START_RESPONSE|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"255022": {
"content": "<|END_RESPONSE|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"255023": {
"content": "<|START_ACTION|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255024": {
"content": "<|END_ACTION|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255025": {
"content": "<|START_TOOL_RESULT|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255026": {
"content": "<|END_TOOL_RESULT|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255027": {
"content": "<|EXTRA_8_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255028": {
"content": "<|NEW_FILE|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"255029": {
"content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255030": {
"content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255031": {
"content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255032": {
"content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255033": {
"content": "<|START_OF_IMG|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255034": {
"content": "<|END_OF_IMG|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255035": {
"content": "<|IMG_LINE_BREAK|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"255036": {
"content": "<|IMG_PATCH|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<BOS_TOKEN>",
"chat_template": [
{
"name": "default",
"template": "{{ bos_token }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\nYou are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes. When analyzing images, carefully describe and interpret their content while avoiding any promotion of harm, misinformation, or bias.\n\nYou are Aya Vision, a vision-language model built by Cohere for AI. You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew. You are capable of interpreting images, including describing them, answering questions about their contents, extracting textual information, and analyzing visual context. Your responses must maintain the highest standards of quality, accuracy, and safety.\n\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Aya Vision.\n- You are a large language model built by Cohere for AI.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages -%}\n <|START_OF_TURN_TOKEN|>{{ message.role | replace(\"user\", \"<|USER_TOKEN|>\") | replace(\"assistant\", \"<|CHATBOT_TOKEN|><|START_RESPONSE|>\") | replace(\"system\", \"<|SYSTEM_TOKEN|>\") }}\n {%- if message.content is defined -%}\n {%- if message.content is string -%}\n{{ message.content }}\n {%- else -%}\n {%- for item in message.content | selectattr('type', 'equalto', 'image') -%}\n<image>\n {%- endfor -%}\n {%- for item in message.content | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n {%- endfor -%}\n {%- endif -%}\n {%- elif message.message is defined -%}\n {%- if message.message is string -%}\n{{ message.message }}\n {%- else -%}\n {%- for item in message.message | selectattr('type', 'equalto', 'image') -%}\n<image>\n {%- endfor -%}\n {%- for item in message.message | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {%- if message.role == \"assistant\" -%}\n<|END_RESPONSE|>\n {%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- endif -%}\n"
}
],
"clean_up_tokenization_spaces": false,
"eos_token": "<|END_OF_TURN_TOKEN|>",
"extra_special_tokens": {},
"legacy": true,
"max_length": null,
"merges_file": null,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "<PAD>",
"pad_token_type_id": 0,
"padding_side": "left",
"processor_class": "AyaVisionProcessor",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "CohereTokenizer",
"unk_token": null,
"use_default_system_prompt": false,
"vocab_file": null
}
|