CoolFace
Modelpublic

TechxGenus/CursorCore-DS-1.3B

sourceHugging Faceotherupdated 2y agoView on Hugging Face
0likes62downloads
tokenizer_config.json282 linesDownload Raw Back to root
1{2  "add_bos_token": true,3  "add_eos_token": false,4  "add_prefix_space": null,5  "added_tokens_decoder": {6    "32000": {7      "content": "õ",8      "lstrip": false,9      "normalized": true,10      "rstrip": false,11      "single_word": false,12      "special": false13    },14    "32001": {15      "content": "÷",16      "lstrip": false,17      "normalized": true,18      "rstrip": false,19      "single_word": false,20      "special": false21    },22    "32002": {23      "content": "Á",24      "lstrip": false,25      "normalized": true,26      "rstrip": false,27      "single_word": false,28      "special": false29    },30    "32003": {31      "content": "ý",32      "lstrip": false,33      "normalized": true,34      "rstrip": false,35      "single_word": false,36      "special": false37    },38    "32004": {39      "content": "À",40      "lstrip": false,41      "normalized": true,42      "rstrip": false,43      "single_word": false,44      "special": false45    },46    "32005": {47      "content": "ÿ",48      "lstrip": false,49      "normalized": true,50      "rstrip": false,51      "single_word": false,52      "special": false53    },54    "32006": {55      "content": "ø",56      "lstrip": false,57      "normalized": true,58      "rstrip": false,59      "single_word": false,60      "special": false61    },62    "32007": {63      "content": "ú",64      "lstrip": false,65      "normalized": true,66      "rstrip": false,67      "single_word": false,68      "special": false69    },70    "32008": {71      "content": "þ",72      "lstrip": false,73      "normalized": true,74      "rstrip": false,75      "single_word": false,76      "special": false77    },78    "32009": {79      "content": "ü",80      "lstrip": false,81      "normalized": true,82      "rstrip": false,83      "single_word": false,84      "special": false85    },86    "32010": {87      "content": "ù",88      "lstrip": false,89      "normalized": true,90      "rstrip": false,91      "single_word": false,92      "special": false93    },94    "32011": {95      "content": "ö",96      "lstrip": false,97      "normalized": true,98      "rstrip": false,99      "single_word": false,100      "special": false101    },102    "32012": {103      "content": "û",104      "lstrip": false,105      "normalized": true,106      "rstrip": false,107      "single_word": false,108      "special": false109    },110    "32013": {111      "content": "<|begin▁of▁sentence|>",112      "lstrip": false,113      "normalized": true,114      "rstrip": false,115      "single_word": false,116      "special": true117    },118    "32014": {119      "content": "<|end▁of▁sentence|>",120      "lstrip": false,121      "normalized": true,122      "rstrip": false,123      "single_word": false,124      "special": true125    },126    "32015": {127      "content": "<|fim▁hole|>",128      "lstrip": false,129      "normalized": true,130      "rstrip": false,131      "single_word": false,132      "special": false133    },134    "32016": {135      "content": "<|fim▁begin|>",136      "lstrip": false,137      "normalized": true,138      "rstrip": false,139      "single_word": false,140      "special": false141    },142    "32017": {143      "content": "<|fim▁end|>",144      "lstrip": false,145      "normalized": true,146      "rstrip": false,147      "single_word": false,148      "special": false149    },150    "32018": {151      "content": "<pad>",152      "lstrip": false,153      "normalized": true,154      "rstrip": false,155      "single_word": false,156      "special": false157    },158    "32019": {159      "content": "<|User|>",160      "lstrip": false,161      "normalized": true,162      "rstrip": false,163      "single_word": false,164      "special": false165    },166    "32020": {167      "content": "<|Assistant|>",168      "lstrip": false,169      "normalized": true,170      "rstrip": false,171      "single_word": false,172      "special": false173    },174    "32021": {175      "content": "<|EOT|>",176      "lstrip": false,177      "normalized": true,178      "rstrip": false,179      "single_word": false,180      "special": false181    },182    "32022": {183      "content": "<|im_end|>",184      "lstrip": false,185      "normalized": false,186      "rstrip": false,187      "single_word": false,188      "special": true189    },190    "32023": {191      "content": "<|im_start|>",192      "lstrip": false,193      "normalized": false,194      "rstrip": false,195      "single_word": false,196      "special": true197    },198    "32024": {199      "content": "<|next_start|>",200      "lstrip": false,201      "normalized": false,202      "rstrip": false,203      "single_word": false,204      "special": true205    },206    "32025": {207      "content": "<|next_end|>",208      "lstrip": false,209      "normalized": false,210      "rstrip": false,211      "single_word": false,212      "special": true213    },214    "32026": {215      "content": "<|target_start|>",216      "lstrip": false,217      "normalized": false,218      "rstrip": false,219      "single_word": false,220      "special": true221    },222    "32027": {223      "content": "<|target_end|>",224      "lstrip": false,225      "normalized": false,226      "rstrip": false,227      "single_word": false,228      "special": true229    },230    "32028": {231      "content": "<|target|>",232      "lstrip": false,233      "normalized": false,234      "rstrip": false,235      "single_word": false,236      "special": true237    },238    "32029": {239      "content": "<|search_and_replace|>",240      "lstrip": false,241      "normalized": false,242      "rstrip": false,243      "single_word": false,244      "special": true245    }246  },247  "additional_special_tokens": [248    "<|im_start|>",249    "<|im_end|>",250    "<|next_start|>",251    "<|next_end|>",252    "<|target_start|>",253    "<|target_end|>",254    "<|target|>",255    "<|search_and_replace|>"256  ],257  "bos_token": "<|begin▁of▁sentence|>",258  "chat_template": [259    {260      "name": "default",261      "template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n' }}{% endif %}{% endfor %}"262    },263    {264      "name": "assistant-conversation",265      "template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n<|next_start|>' }}{% endif %}{% endfor %}"266    },267    {268      "name": "prefix_response",269      "template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] }}{% if not loop.last %}{{ '<|im_end|>' }}{% endif %}{% endfor %}"270    }271  ],272  "clean_up_tokenization_spaces": false,273  "eos_token": "<|im_end|>",274  "legacy": true,275  "model_max_length": 16384,276  "pad_token": "<|end▁of▁sentence|>",277  "sp_model_kwargs": {},278  "tokenizer_class": "LlamaTokenizer",279  "unk_token": null,280  "use_default_system_prompt": false281}282