tokenizer_config.json
| 1 | { |
| 2 | "add_bos_token": true, |
| 3 | "add_eos_token": false, |
| 4 | "added_tokens_decoder": { |
| 5 | "0": { |
| 6 | "content": "<unk>", |
| 7 | "lstrip": false, |
| 8 | "normalized": false, |
| 9 | "rstrip": false, |
| 10 | "single_word": false, |
| 11 | "special": true |
| 12 | }, |
| 13 | "1": { |
| 14 | "content": "<s>", |
| 15 | "lstrip": false, |
| 16 | "normalized": false, |
| 17 | "rstrip": false, |
| 18 | "single_word": false, |
| 19 | "special": true |
| 20 | }, |
| 21 | "2": { |
| 22 | "content": "</s>", |
| 23 | "lstrip": false, |
| 24 | "normalized": false, |
| 25 | "rstrip": false, |
| 26 | "single_word": false, |
| 27 | "special": true |
| 28 | }, |
| 29 | "101": { |
| 30 | "content": "<|audio_start|>", |
| 31 | "lstrip": false, |
| 32 | "normalized": false, |
| 33 | "rstrip": false, |
| 34 | "single_word": false, |
| 35 | "special": true |
| 36 | }, |
| 37 | "102": { |
| 38 | "content": "<|audio_end|>", |
| 39 | "lstrip": false, |
| 40 | "normalized": false, |
| 41 | "rstrip": false, |
| 42 | "single_word": false, |
| 43 | "special": true |
| 44 | }, |
| 45 | "103": { |
| 46 | "content": "<|audio_prompt_start|>", |
| 47 | "lstrip": false, |
| 48 | "normalized": false, |
| 49 | "rstrip": false, |
| 50 | "single_word": false, |
| 51 | "special": true |
| 52 | }, |
| 53 | "104": { |
| 54 | "content": "<|audio_prompt_end|>", |
| 55 | "lstrip": false, |
| 56 | "normalized": false, |
| 57 | "rstrip": false, |
| 58 | "single_word": false, |
| 59 | "special": true |
| 60 | }, |
| 61 | "105": { |
| 62 | "content": "<|background|>", |
| 63 | "lstrip": false, |
| 64 | "normalized": false, |
| 65 | "rstrip": false, |
| 66 | "single_word": false, |
| 67 | "special": true |
| 68 | }, |
| 69 | "106": { |
| 70 | "content": "<|/background|>", |
| 71 | "lstrip": false, |
| 72 | "normalized": false, |
| 73 | "rstrip": false, |
| 74 | "single_word": false, |
| 75 | "special": true |
| 76 | }, |
| 77 | "107": { |
| 78 | "content": "<|characters|>", |
| 79 | "lstrip": false, |
| 80 | "normalized": false, |
| 81 | "rstrip": false, |
| 82 | "single_word": false, |
| 83 | "special": true |
| 84 | }, |
| 85 | "108": { |
| 86 | "content": "<|/characters|>", |
| 87 | "lstrip": false, |
| 88 | "normalized": false, |
| 89 | "rstrip": false, |
| 90 | "single_word": false, |
| 91 | "special": true |
| 92 | }, |
| 93 | "109": { |
| 94 | "content": "<|speaker_id|>", |
| 95 | "lstrip": false, |
| 96 | "normalized": false, |
| 97 | "rstrip": false, |
| 98 | "single_word": false, |
| 99 | "special": true |
| 100 | }, |
| 101 | "110": { |
| 102 | "content": "<|/speaker_id|>", |
| 103 | "lstrip": false, |
| 104 | "normalized": false, |
| 105 | "rstrip": false, |
| 106 | "single_word": false, |
| 107 | "special": true |
| 108 | }, |
| 109 | "111": { |
| 110 | "content": "<|span|>", |
| 111 | "lstrip": false, |
| 112 | "normalized": false, |
| 113 | "rstrip": false, |
| 114 | "single_word": false, |
| 115 | "special": true |
| 116 | }, |
| 117 | "112": { |
| 118 | "content": "<|/span|>", |
| 119 | "lstrip": false, |
| 120 | "normalized": false, |
| 121 | "rstrip": false, |
| 122 | "single_word": false, |
| 123 | "special": true |
| 124 | }, |
| 125 | "73440": { |
| 126 | "content": "<|im_end|>", |
| 127 | "lstrip": false, |
| 128 | "normalized": false, |
| 129 | "rstrip": false, |
| 130 | "single_word": false, |
| 131 | "special": true |
| 132 | }, |
| 133 | "73441": { |
| 134 | "content": "<|im_start|>", |
| 135 | "lstrip": false, |
| 136 | "normalized": false, |
| 137 | "rstrip": false, |
| 138 | "single_word": false, |
| 139 | "special": true |
| 140 | }, |
| 141 | "73442": { |
| 142 | "content": "<|tool_call|>", |
| 143 | "lstrip": false, |
| 144 | "normalized": false, |
| 145 | "rstrip": false, |
| 146 | "single_word": false, |
| 147 | "special": true |
| 148 | }, |
| 149 | "73443": { |
| 150 | "content": "<|execute_start|>", |
| 151 | "lstrip": false, |
| 152 | "normalized": false, |
| 153 | "rstrip": false, |
| 154 | "single_word": false, |
| 155 | "special": true |
| 156 | }, |
| 157 | "73444": { |
| 158 | "content": "<|execute_end|>", |
| 159 | "lstrip": false, |
| 160 | "normalized": false, |
| 161 | "rstrip": false, |
| 162 | "single_word": false, |
| 163 | "special": true |
| 164 | }, |
| 165 | "73445": { |
| 166 | "content": "<|fim_prefix|>", |
| 167 | "lstrip": false, |
| 168 | "normalized": false, |
| 169 | "rstrip": false, |
| 170 | "single_word": false, |
| 171 | "special": true |
| 172 | }, |
| 173 | "73446": { |
| 174 | "content": "<|fim_middle|>", |
| 175 | "lstrip": false, |
| 176 | "normalized": false, |
| 177 | "rstrip": false, |
| 178 | "single_word": false, |
| 179 | "special": true |
| 180 | }, |
| 181 | "73447": { |
| 182 | "content": "<|fim_suffix|>", |
| 183 | "lstrip": false, |
| 184 | "normalized": false, |
| 185 | "rstrip": false, |
| 186 | "single_word": false, |
| 187 | "special": true |
| 188 | } |
| 189 | }, |
| 190 | "additional_special_tokens": [ |
| 191 | "<|im_end|>", |
| 192 | "<|im_start|>", |
| 193 | "<|tool_call|>", |
| 194 | "<|execute_start|>", |
| 195 | "<|execute_end|>", |
| 196 | "<|fim_prefix|>", |
| 197 | "<|fim_middle|>", |
| 198 | "<|fim_suffix|>" |
| 199 | ], |
| 200 | "bos_token": "<s>", |
| 201 | "clean_up_tokenization_spaces": false, |
| 202 | "eos_token": "<|im_end|>", |
| 203 | "legacy": true, |
| 204 | "model_max_length": 1000000000000000019884624838656, |
| 205 | "pad_token": null, |
| 206 | "sp_model_kwargs": {}, |
| 207 | "spaces_between_special_tokens": false, |
| 208 | "tokenizer_class": "VoxCPM2Tokenizer", |
| 209 | "unk_token": "<unk>", |
| 210 | "use_default_system_prompt": false, |
| 211 | "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", |
| 212 | "auto_map": { |
| 213 | "AutoTokenizer": [ |
| 214 | "tokenization_voxcpm2.VoxCPM2Tokenizer", |
| 215 | null |
| 216 | ] |
| 217 | } |
| 218 | } |
| 219 | |