CoolFace
Modelpublic

kernelPanicAtTheDisco/NuExtract-2-4B-NFA

sourceHugging Facemitupdated 1y agoView on Hugging Face
0likes11downloads
tokenizer_config.json290 linesDownload Raw Back to root
1{2  "add_bos_token": false,3  "add_eos_token": false,4  "add_prefix_space": false,5  "added_tokens_decoder": {6    "151643": {7      "content": "<|endoftext|>",8      "lstrip": false,9      "normalized": false,10      "rstrip": false,11      "single_word": false,12      "special": true13    },14    "151644": {15      "content": "<|im_start|>",16      "lstrip": false,17      "normalized": false,18      "rstrip": false,19      "single_word": false,20      "special": true21    },22    "151645": {23      "content": "<|im_end|>",24      "lstrip": false,25      "normalized": false,26      "rstrip": false,27      "single_word": false,28      "special": true29    },30    "151646": {31      "content": "<|object_ref_start|>",32      "lstrip": false,33      "normalized": false,34      "rstrip": false,35      "single_word": false,36      "special": true37    },38    "151647": {39      "content": "<|object_ref_end|>",40      "lstrip": false,41      "normalized": false,42      "rstrip": false,43      "single_word": false,44      "special": true45    },46    "151648": {47      "content": "<|box_start|>",48      "lstrip": false,49      "normalized": false,50      "rstrip": false,51      "single_word": false,52      "special": true53    },54    "151649": {55      "content": "<|box_end|>",56      "lstrip": false,57      "normalized": false,58      "rstrip": false,59      "single_word": false,60      "special": true61    },62    "151650": {63      "content": "<|quad_start|>",64      "lstrip": false,65      "normalized": false,66      "rstrip": false,67      "single_word": false,68      "special": true69    },70    "151651": {71      "content": "<|quad_end|>",72      "lstrip": false,73      "normalized": false,74      "rstrip": false,75      "single_word": false,76      "special": true77    },78    "151652": {79      "content": "<|vision_start|>",80      "lstrip": false,81      "normalized": false,82      "rstrip": false,83      "single_word": false,84      "special": true85    },86    "151653": {87      "content": "<|vision_end|>",88      "lstrip": false,89      "normalized": false,90      "rstrip": false,91      "single_word": false,92      "special": true93    },94    "151654": {95      "content": "<|vision_pad|>",96      "lstrip": false,97      "normalized": false,98      "rstrip": false,99      "single_word": false,100      "special": true101    },102    "151655": {103      "content": "<|image_pad|>",104      "lstrip": false,105      "normalized": false,106      "rstrip": false,107      "single_word": false,108      "special": true109    },110    "151656": {111      "content": "<|video_pad|>",112      "lstrip": false,113      "normalized": false,114      "rstrip": false,115      "single_word": false,116      "special": true117    },118    "151657": {119      "content": "<tool_call>",120      "lstrip": false,121      "normalized": false,122      "rstrip": false,123      "single_word": false,124      "special": false125    },126    "151658": {127      "content": "</tool_call>",128      "lstrip": false,129      "normalized": false,130      "rstrip": false,131      "single_word": false,132      "special": false133    },134    "151659": {135      "content": "<|fim_prefix|>",136      "lstrip": false,137      "normalized": false,138      "rstrip": false,139      "single_word": false,140      "special": false141    },142    "151660": {143      "content": "<|fim_middle|>",144      "lstrip": false,145      "normalized": false,146      "rstrip": false,147      "single_word": false,148      "special": false149    },150    "151661": {151      "content": "<|fim_suffix|>",152      "lstrip": false,153      "normalized": false,154      "rstrip": false,155      "single_word": false,156      "special": false157    },158    "151662": {159      "content": "<|fim_pad|>",160      "lstrip": false,161      "normalized": false,162      "rstrip": false,163      "single_word": false,164      "special": false165    },166    "151663": {167      "content": "<|repo_name|>",168      "lstrip": false,169      "normalized": false,170      "rstrip": false,171      "single_word": false,172      "special": false173    },174    "151664": {175      "content": "<|file_sep|>",176      "lstrip": false,177      "normalized": false,178      "rstrip": false,179      "single_word": false,180      "special": false181    },182    "151665": {183      "content": "<img>",184      "lstrip": false,185      "normalized": false,186      "rstrip": false,187      "single_word": false,188      "special": true189    },190    "151666": {191      "content": "</img>",192      "lstrip": false,193      "normalized": false,194      "rstrip": false,195      "single_word": false,196      "special": true197    },198    "151667": {199      "content": "<IMG_CONTEXT>",200      "lstrip": false,201      "normalized": false,202      "rstrip": false,203      "single_word": false,204      "special": true205    },206    "151668": {207      "content": "<quad>",208      "lstrip": false,209      "normalized": false,210      "rstrip": false,211      "single_word": false,212      "special": true213    },214    "151669": {215      "content": "</quad>",216      "lstrip": false,217      "normalized": false,218      "rstrip": false,219      "single_word": false,220      "special": true221    },222    "151670": {223      "content": "<ref>",224      "lstrip": false,225      "normalized": false,226      "rstrip": false,227      "single_word": false,228      "special": true229    },230    "151671": {231      "content": "</ref>",232      "lstrip": false,233      "normalized": false,234      "rstrip": false,235      "single_word": false,236      "special": true237    },238    "151672": {239      "content": "<box>",240      "lstrip": false,241      "normalized": false,242      "rstrip": false,243      "single_word": false,244      "special": true245    },246    "151673": {247      "content": "</box>",248      "lstrip": false,249      "normalized": false,250      "rstrip": false,251      "single_word": false,252      "special": true253    }254  },255  "additional_special_tokens": [256    "<|im_start|>",257    "<|im_end|>",258    "<|object_ref_start|>",259    "<|object_ref_end|>",260    "<|box_start|>",261    "<|box_end|>",262    "<|quad_start|>",263    "<|quad_end|>",264    "<|vision_start|>",265    "<|vision_end|>",266    "<|vision_pad|>",267    "<|image_pad|>",268    "<|video_pad|>",269    "<img>",270    "</img>",271    "<IMG_CONTEXT>",272    "<quad>",273    "</quad>",274    "<ref>",275    "</ref>",276    "<box>",277    "</box>"278  ],279  "bos_token": null,280  "chat_template": "{% for message in messages %}\n    {%- if message['role'] == 'user' and template -%}\n        {{- '<|im_start|>' + message['role'] -}}\n        {{ '\n# Template:' }}\n        {{- '\n' + template }}\n        {% if examples %}\n            {{- '# Examples:' }}\n            {% for example in examples %}\n                {{- '## Input:\n' }}\n                {{- example['input'] + '\n' }}\n                {{- '## Output:\n' }}\n                {{- example['output'] | trim }}\n            {% endfor %}\n        {%- endif %}\n        {{- '# Context:' }}\n        {% if message['content'] is string %}\n            {{- message['content'] | trim }}\n        {% else %}\n            {% for content in message['content'] %}\n                {%- if content is string %}\n                    {{- content | trim }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] | trim }}\n                {%- endif %}\n            {% endfor %}\n        {% endif %}\n        {{- '<|im_end|> '}}\n    {% else %}\n        {{- '<|im_start|>' + message['role'] }}\n        {% if message['content'] is string %}\n            {{- message['content'] | trim }}\n        {% else %}\n            {% for content in message['content'] %}\n                {%- if content is string %}\n                    {{- content | trim }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] | trim }}\n                {%- endif %}\n            {% endfor %}\n        {% endif %}\n        {{- '<|im_end|> '}}\n    {% endif %}\n{% endfor -%}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant' }}\n{% endif -%}\n",281  "clean_up_tokenization_spaces": false,282  "eos_token": "<|im_end|>",283  "errors": "replace",284  "extra_special_tokens": {},285  "model_max_length": 16384,286  "pad_token": "<|endoftext|>",287  "split_special_tokens": false,288  "tokenizer_class": "Qwen2Tokenizer",289  "unk_token": null290}