SPB Git

Repository Public Research preview

tokenizer_config.json 2.8 KB 157 lines json

1{2  "type": "sentencepiece",3  "model_type": "unigram",4  "vocab_size": 32000,5  "pad_id": 0,6  "bos_id": 1,7  "eos_id": 2,8  "unk_id": 3,9  "control_tokens": [10    "<disc:biomedicine>",11    "<disc:life_sciences>",12    "<disc:physics>",13    "<disc:mathematics>",14    "<disc:computer_science>",15    "<disc:statistics>",16    "<disc:economics>",17    "<disc:finance>",18    "<disc:social_sciences>",19    "<disc:engineering>",20    "<disc:chemistry>",21    "<disc:earth_sciences>",22    "<disc:humanities>",23    "<disc:general_reference>",24    "<disc:other>",25    "<disc:unknown>",26    "<era:pre1900>",27    "<era:1900-1949>",28    "<era:1950-1979>",29    "<era:1980-1999>",30    "<era:2000-2009>",31    "<era:2010-2017>",32    "<era:unknown>",33    "<era:post2017>",34    "<role:abstract>",35    "<role:introduction>",36    "<role:background>",37    "<role:methods>",38    "<role:results>",39    "<role:discussion>",40    "<role:conclusion>",41    "<role:related_work>",42    "<role:theory>",43    "<role:data>",44    "<role:limitations>",45    "<role:other>",46    "<role:caption>",47    "<role:chapter>",48    "<role:preface>",49    "<src:pmc>",50    "<src:arxiv>",51    "<src:crossref>",52    "<src:bookshelf>",53    "<src:openstax>",54    "<src:gutenberg>",55    "<src:local>",56    "<src:mock>",57    "⟦C1⟧",58    "⟦C2⟧",59    "⟦C3⟧",60    "⟦C4⟧",61    "⟦C5⟧",62    "⟦C6⟧",63    "⟦C7⟧",64    "⟦C8⟧",65    "⟦C9⟧",66    "⟦C10⟧",67    "⟦C11⟧",68    "⟦C12⟧",69    "⟦C13⟧",70    "⟦C14⟧",71    "⟦C15⟧",72    "⟦C16⟧",73    "⟦C17⟧",74    "⟦C18⟧",75    "⟦C19⟧",76    "⟦C20⟧",77    "⟦C21⟧",78    "⟦C22⟧",79    "⟦C23⟧",80    "⟦C24⟧",81    "⟦C25⟧",82    "⟦C26⟧",83    "⟦C27⟧",84    "⟦C28⟧",85    "⟦C29⟧",86    "⟦C30⟧",87    "⟦C31⟧",88    "⟦C32⟧",89    "⟦M1⟧",90    "⟦M2⟧",91    "⟦M3⟧",92    "⟦M4⟧",93    "⟦M5⟧",94    "⟦M6⟧",95    "⟦M7⟧",96    "⟦M8⟧",97    "⟦M9⟧",98    "⟦M10⟧",99    "⟦M11⟧",100    "⟦M12⟧",101    "⟦M13⟧",102    "⟦M14⟧",103    "⟦M15⟧",104    "⟦M16⟧",105    "⟦M17⟧",106    "⟦M18⟧",107    "⟦M19⟧",108    "⟦M20⟧",109    "⟦M21⟧",110    "⟦M22⟧",111    "⟦M23⟧",112    "⟦M24⟧",113    "⟦M25⟧",114    "⟦M26⟧",115    "⟦M27⟧",116    "⟦M28⟧",117    "⟦M29⟧",118    "⟦M30⟧",119    "⟦M31⟧",120    "⟦M32⟧",121    "⟦U1⟧",122    "⟦U2⟧",123    "⟦U3⟧",124    "⟦U4⟧",125    "⟦U5⟧",126    "⟦U6⟧",127    "⟦U7⟧",128    "⟦U8⟧",129    "⟦U9⟧",130    "⟦U10⟧",131    "⟦U11⟧",132    "⟦U12⟧",133    "⟦U13⟧",134    "⟦U14⟧",135    "⟦U15⟧",136    "⟦U16⟧",137    "⟦U17⟧",138    "⟦U18⟧",139    "⟦U19⟧",140    "⟦U20⟧",141    "⟦U21⟧",142    "⟦U22⟧",143    "⟦U23⟧",144    "⟦U24⟧",145    "⟦U25⟧",146    "⟦U26⟧",147    "⟦U27⟧",148    "⟦U28⟧",149    "⟦U29⟧",150    "⟦U30⟧",151    "⟦U31⟧",152    "⟦U32⟧",153    "<sep>",154    "<meta>",155    "</meta>"156  ]157}
Files main
Menu

Theme