File size: 8,888 Bytes
6c5308a 2cb186e 6c5308a |
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 |
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "<|im_start|>user\nYou are an expert in content safety evaluation, possessing strong language comprehension and risk identification skills.\nYour task is to classify the provided input text into the most appropriate category from the list below as part of a safety audit project.\n\n# Category List\n- sec: Safe\n- pc: Pornographic Contraband\n- dc: Drug Crimes\n- dw: Dangerous Weapons\n- pi: Property Infringement\n- ec: Economic Crimes\n- ac: Abusive Curses\n- def: Defamation\n- ti: Threats and Intimidation\n- cy: Cyberbullying\n- ph: Physical Health\n- mh: Mental Health\n- se: Social Ethics\n- sci: Science Ethics\n- pp: Personal Privacy\n- cs: Commercial Secret\n- acc: Access Control\n- mc: Malicious Code\n- ha: Hacker Attack\n- ps: Physical Security\n- ter: Violent Terrorist Activities\n- sd: Social Disruption\n- ext: Extremist Ideological Trends\n- fin: Finance\n- med: Medicine\n- law: Law\n- cm: Corruption of Minors\n- ma: Minor Abuse and Exploitation\n- md: Minor Delinquency\n{% if policy is defined and policy %}\n\n# Dynamic Policy\n{{ policy | trim }}\n{% endif %}\n\n# Instructions\n{% if reason_first %}\n- Provide a concise justification for your choice, placing it between <explanation> and </explanation> tags.\n- On the next line, identify the single most relevant category ID for the input text.\n{% else %}\n- Identify the single most relevant category ID for the input text.\n- On the next line, provide a concise justification for your choice, placing it between <explanation> and </explanation> tags.\n{% endif %}\n\n---\n\nInput Text: {% if messages is sequence and messages is not string and (messages|length) == 1 %}{{ messages[0].content | default(\"\") | trim }}{% elif messages is sequence and messages is not string and (messages|length) > 1 %}[User Query] {{ messages[0].content | default(\"\") | trim }}\n\n[LLM Response] {{ messages[1].content | default(\"\") | trim }}{% endif %}<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>{{ \"\n\n\" }}",
"id2risk": {
"sec": "Safe-Safe",
"pc": "Crimes and Illegal Activities-Pornographic Contraband",
"dc": "Crimes and Illegal Activities-Drug Crimes",
"dw": "Crimes and Illegal Activities-Dangerous Weapons",
"pi": "Crimes and Illegal Activities-Property Infringement",
"ec": "Crimes and Illegal Activities-Economic Crimes",
"ac": "Hate Speech-Abusive Curses",
"def": "Hate Speech-Defamation",
"ti": "Hate Speech-Threats and Intimidation",
"cy": "Hate Speech-Cyberbullying",
"ph": "Physical and Mental Health-Physical Health",
"mh": "Physical and Mental Health-Mental Health",
"se": "Ethics and Morality-Social Ethics",
"sci": "Ethics and Morality-Science Ethics",
"pp": "Data Privacy-Personal Privacy",
"cs": "Data Privacy-Commercial Secret",
"acc": "Cybersecurity-Access Control",
"mc": "Cybersecurity-Malicious Code",
"ha": "Cybersecurity-Hacker Attack",
"ps": "Cybersecurity-Physical Security",
"ter": "Extremism-Violent Terrorist Activities",
"sd": "Extremism-Social Disruption",
"ext": "Extremism-Extremist Ideological Trends",
"fin": "Inappropriate Suggestions-Finance",
"med": "Inappropriate Suggestions-Medicine",
"law": "Inappropriate Suggestions-Law",
"cm": "Risks Involving Minors-Corruption of Minors",
"ma": "Risks Involving Minors-Minor Abuse and Exploitation",
"md": "Risks Involving Minors-Minor Delinquency"
},
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}
|