CoolFace
Modelpublic

dots-studio/dots.mocr

sourceHugging Facemitupdated 3mo agoView on Hugging Face
178likes449kdownloads
tokenizer_config.json392 linesDownload Raw Back to root
1{2  "add_bos_token": false,3  "add_prefix_space": false,4  "added_tokens_decoder": {5    "151643": {6      "content": "<|endoftext|>",7      "lstrip": false,8      "normalized": false,9      "rstrip": false,10      "single_word": false,11      "special": true12    },13    "151644": {14      "content": "<|im_start|>",15      "lstrip": false,16      "normalized": false,17      "rstrip": false,18      "single_word": false,19      "special": true20    },21    "151645": {22      "content": "<|im_end|>",23      "lstrip": false,24      "normalized": false,25      "rstrip": false,26      "single_word": false,27      "special": true28    },29    "151646": {30      "content": "<|object_ref_start|>",31      "lstrip": false,32      "normalized": false,33      "rstrip": false,34      "single_word": false,35      "special": true36    },37    "151647": {38      "content": "<|object_ref_end|>",39      "lstrip": false,40      "normalized": false,41      "rstrip": false,42      "single_word": false,43      "special": true44    },45    "151648": {46      "content": "<|box_start|>",47      "lstrip": false,48      "normalized": false,49      "rstrip": false,50      "single_word": false,51      "special": true52    },53    "151649": {54      "content": "<|box_end|>",55      "lstrip": false,56      "normalized": false,57      "rstrip": false,58      "single_word": false,59      "special": true60    },61    "151650": {62      "content": "<|quad_start|>",63      "lstrip": false,64      "normalized": false,65      "rstrip": false,66      "single_word": false,67      "special": true68    },69    "151651": {70      "content": "<|quad_end|>",71      "lstrip": false,72      "normalized": false,73      "rstrip": false,74      "single_word": false,75      "special": true76    },77    "151652": {78      "content": "<|vision_start|>",79      "lstrip": false,80      "normalized": false,81      "rstrip": false,82      "single_word": false,83      "special": true84    },85    "151653": {86      "content": "<|vision_end|>",87      "lstrip": false,88      "normalized": false,89      "rstrip": false,90      "single_word": false,91      "special": true92    },93    "151654": {94      "content": "<|vision_pad|>",95      "lstrip": false,96      "normalized": false,97      "rstrip": false,98      "single_word": false,99      "special": true100    },101    "151655": {102      "content": "<|image_pad|>",103      "lstrip": false,104      "normalized": false,105      "rstrip": false,106      "single_word": false,107      "special": true108    },109    "151656": {110      "content": "<|video_pad|>",111      "lstrip": false,112      "normalized": false,113      "rstrip": false,114      "single_word": false,115      "special": true116    },117    "151657": {118      "content": "<tool_call>",119      "lstrip": false,120      "normalized": false,121      "rstrip": false,122      "single_word": false,123      "special": false124    },125    "151658": {126      "content": "</tool_call>",127      "lstrip": false,128      "normalized": false,129      "rstrip": false,130      "single_word": false,131      "special": false132    },133    "151659": {134      "content": "<|fim_prefix|>",135      "lstrip": false,136      "normalized": false,137      "rstrip": false,138      "single_word": false,139      "special": false140    },141    "151660": {142      "content": "<|fim_middle|>",143      "lstrip": false,144      "normalized": false,145      "rstrip": false,146      "single_word": false,147      "special": false148    },149    "151661": {150      "content": "<|fim_suffix|>",151      "lstrip": false,152      "normalized": false,153      "rstrip": false,154      "single_word": false,155      "special": false156    },157    "151662": {158      "content": "<|fim_pad|>",159      "lstrip": false,160      "normalized": false,161      "rstrip": false,162      "single_word": false,163      "special": false164    },165    "151663": {166      "content": "<|repo_name|>",167      "lstrip": false,168      "normalized": false,169      "rstrip": false,170      "single_word": false,171      "special": false172    },173    "151664": {174      "content": "<|file_sep|>",175      "lstrip": false,176      "normalized": false,177      "rstrip": false,178      "single_word": false,179      "special": false180    },181    "151665": {182      "content": "<|imgpad|>",183      "lstrip": false,184      "normalized": false,185      "rstrip": false,186      "single_word": false,187      "special": true188    },189    "151666": {190      "content": "<|img|>",191      "lstrip": false,192      "normalized": false,193      "rstrip": false,194      "single_word": false,195      "special": true196    },197    "151667": {198      "content": "<|endofimg|>",199      "lstrip": false,200      "normalized": false,201      "rstrip": false,202      "single_word": false,203      "special": true204    },205    "151668": {206      "content": "<|systemprompt|>",207      "lstrip": false,208      "normalized": false,209      "rstrip": false,210      "single_word": false,211      "special": true212    },213    "151669": {214      "content": "<|endofsystemprompt|>",215      "lstrip": false,216      "normalized": false,217      "rstrip": false,218      "single_word": false,219      "special": true220    },221    "151670": {222      "content": "<|user|>",223      "lstrip": false,224      "normalized": false,225      "rstrip": false,226      "single_word": false,227      "special": true228    },229    "151671": {230      "content": "<|endofuser|>",231      "lstrip": false,232      "normalized": false,233      "rstrip": false,234      "single_word": false,235      "special": true236    },237    "151672": {238      "content": "<|assistant|>",239      "lstrip": false,240      "normalized": false,241      "rstrip": false,242      "single_word": false,243      "special": true244    },245    "151673": {246      "content": "<|endofassistant|>",247      "lstrip": false,248      "normalized": false,249      "rstrip": false,250      "single_word": false,251      "special": true252    },253    "151674": {254      "content": "<|ref_start|>",255      "lstrip": false,256      "normalized": false,257      "rstrip": false,258      "single_word": false,259      "special": true260    },261    "151675": {262      "content": "<|ref_end|>",263      "lstrip": false,264      "normalized": false,265      "rstrip": false,266      "single_word": false,267      "special": true268    },269    "151676": {270      "content": "[SEP]",271      "lstrip": false,272      "normalized": false,273      "rstrip": false,274      "single_word": false,275      "special": true276    },277    "151677": {278      "content": "<|pic|>",279      "lstrip": false,280      "normalized": false,281      "rstrip": false,282      "single_word": false,283      "special": true284    },285    "151678": {286      "content": "<|text|>",287      "lstrip": false,288      "normalized": false,289      "rstrip": false,290      "single_word": false,291      "special": true292    },293    "151679": {294      "content": "<|pictotext|>",295      "lstrip": false,296      "normalized": false,297      "rstrip": false,298      "single_word": false,299      "special": true300    },301    "151680": {302      "content": "[PAD]",303      "lstrip": false,304      "normalized": false,305      "rstrip": false,306      "single_word": false,307      "special": true308    },309    "151681": {310      "content": "<|slice|>",311      "lstrip": false,312      "normalized": false,313      "rstrip": false,314      "single_word": false,315      "special": true316    },317    "151682": {318      "content": "<|endofslice|>",319      "lstrip": false,320      "normalized": false,321      "rstrip": false,322      "single_word": false,323      "special": true324    },325    "151683": {326      "content": "<|imgrowend|>",327      "lstrip": false,328      "normalized": false,329      "rstrip": false,330      "single_word": false,331      "special": true332    },333    "151684": {334      "content": "<|polygon_start|>",335      "lstrip": false,336      "normalized": false,337      "rstrip": false,338      "single_word": false,339      "special": true340    },341    "151685": {342      "content": "<|polygon_end|>",343      "lstrip": false,344      "normalized": false,345      "rstrip": false,346      "single_word": false,347      "special": true348    },349    "151686": {350      "content": "<|image_gen_start|>",351      "lstrip": false,352      "normalized": false,353      "rstrip": false,354      "single_word": false,355      "special": true356    },357    "151687": {358      "content": "<|image_gen_end|>",359      "lstrip": false,360      "normalized": false,361      "rstrip": false,362      "single_word": false,363      "special": true364    }365  },366  "additional_special_tokens": [367    "<|im_start|>",368    "<|im_end|>",369    "<|object_ref_start|>",370    "<|object_ref_end|>",371    "<|box_start|>",372    "<|box_end|>",373    "<|quad_start|>",374    "<|quad_end|>",375    "<|vision_start|>",376    "<|vision_end|>",377    "<|vision_pad|>",378    "<|image_pad|>",379    "<|video_pad|>"380  ],381  "bos_token": null,382  "chat_template": "{%- for m in messages %}\n    {%- if m.role == 'system' %}\n        {{- '<|system|>' + m.content + '<|endofsystem|>\\n' }}\n    {%- elif m.role == 'user' %}\n        {{- '<|user|>' + m.content + '<|endofuser|>' }}\n    {%- elif m.role == 'assistant' %}\n        {{- '<|assistant|>' + m.content }}\n        {%- if not loop.last %}\n            {{- '<|endofassistant|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if messages[-1].role != 'assistant' %}\n    {{- '<|assistant|>' }}\n{%- endif %}",383  "clean_up_tokenization_spaces": false,384  "eos_token": "<|endoftext|>",385  "errors": "replace",386  "model_max_length": 131072,387  "pad_token": "[PAD]",388  "split_special_tokens": false,389  "tokenizer_class": "Qwen2Tokenizer",390  "unk_token": null391}392