Buckets:
| import{s as Mr,o as Pr,n as It}from"../chunks/scheduler.7c59faff.js";import{S as Lr,i as Ir,e as s,s as r,c as h,h as jr,a as i,d as l,b as o,f as b,g,j as T,k as e,l as q,m as f,t as x,n as $,o as _,p}from"../chunks/index.09bb5655.js";import{T as Hr}from"../chunks/Tip.25c348e8.js";import{C as Vr,H as Dr,E as Gr}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.7f4075ae.js";import{D as w}from"../chunks/Docstring.0f892337.js";import{C as Sr}from"../chunks/CodeBlock.61865591.js";import{T as Zr,M as Wn}from"../chunks/TokenizersLanguageContent.0fc17a7a.js";import{E as Ar}from"../chunks/ExampleCodeBlock.66eafe9b.js";function Ur(E){let n,m="Example:",t,u,k;return u=new Sr({props:{code:"ZnJvbSUyMHRva2VuaXplcnMlMjBpbXBvcnQlMjBUb2tlbml6ZXIlMEF0b2tlbml6ZXIlMjAlM0QlMjBUb2tlbml6ZXIuZnJvbV9wcmV0cmFpbmVkKCUyMmJlcnQtYmFzZS11bmNhc2VkJTIyKSUwQWVuY29kaW5nJTIwJTNEJTIwdG9rZW5pemVyLmVuY29kZSglMjJIZWxsbyUyQyUyMHdvcmxkISUyMiklMEFlbmNvZGluZy5pZHMlMEFlbmNvZGluZy50b2tlbnMlMEFlbmNvZGluZy5vZmZzZXRz",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers <span class="hljs-keyword">import</span> Tokenizer | |
| <span class="hljs-meta">>>> </span>tokenizer = Tokenizer.from_pretrained(<span class="hljs-string">"bert-base-uncased"</span>) | |
| <span class="hljs-meta">>>> </span>encoding = tokenizer.encode(<span class="hljs-string">"Hello, world!"</span>) | |
| <span class="hljs-meta">>>> </span>encoding.ids | |
| [<span class="hljs-number">101</span>, <span class="hljs-number">7592</span>, <span class="hljs-number">1010</span>, <span class="hljs-number">2088</span>, <span class="hljs-number">999</span>, <span class="hljs-number">102</span>] | |
| <span class="hljs-meta">>>> </span>encoding.tokens | |
| [<span class="hljs-string">'[CLS]'</span>, <span class="hljs-string">'hello'</span>, <span class="hljs-string">','</span>, <span class="hljs-string">'world'</span>, <span class="hljs-string">'!'</span>, <span class="hljs-string">'[SEP]'</span>] | |
| <span class="hljs-meta">>>> </span>encoding.offsets | |
| [(<span class="hljs-number">0</span>, <span class="hljs-number">0</span>), (<span class="hljs-number">0</span>, <span class="hljs-number">5</span>), (<span class="hljs-number">5</span>, <span class="hljs-number">6</span>), (<span class="hljs-number">7</span>, <span class="hljs-number">12</span>), (<span class="hljs-number">12</span>, <span class="hljs-number">13</span>), (<span class="hljs-number">0</span>, <span class="hljs-number">0</span>)]`,lang:"python",wrap:!1}}),{c(){n=s("p"),n.textContent=m,t=r(),h(u.$$.fragment)},l(v){n=i(v,"P",{"data-svelte-h":!0}),p(n)!=="svelte-11lpom8"&&(n.textContent=m),t=o(v),g(u.$$.fragment,v)},m(v,D){q(v,n,D),q(v,t,D),f(u,v,D),k=!0},p:It,i(v){k||(x(u.$$.fragment,v),k=!0)},o(v){$(u.$$.fragment,v),k=!1},d(v){v&&(l(n),l(t)),_(u,v)}}}function Wr(E){let n,m=`This is deprecated and will be removed in a future version. | |
| Please use <code>~tokenizers.Encoding.word_ids</code> instead.`;return{c(){n=s("p"),n.innerHTML=m},l(t){n=i(t,"P",{"data-svelte-h":!0}),p(n)!=="svelte-1tdbt0g"&&(n.innerHTML=m)},m(t,u){q(t,n,u)},p:It,d(t){t&&l(n)}}}function Fr(E){let n,m,t,u,k,v,D='The <a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a> represents the output of a <a href="/docs/tokenizers/pr_2049/en/api/tokenizer#tokenizers.Tokenizer">Tokenizer</a>.',Y,C,ce=`It holds all the information about the tokenized input, including the token IDs, | |
| token strings, attention masks, offsets, and more. This is the main data structure | |
| returned by <code>encode()</code> and | |
| <code>encode_batch()</code>.`,j,P,X,y,c,z,Q,Fn="The attention mask",jt,Me,Jn=`This indicates to the LM which tokens should be attended to, and which should not. | |
| This is especially important when batching sequences, where we need to applying | |
| padding.`,Ht,H,pe,Vt,Pe,Nn="The generated IDs",Gt,Le,Bn=`The IDs are the main input to a Language Model. They are the token indices, | |
| the numerical representations that a LM understands.`,St,K,le,Zt,Ie,Xn="The number of sequences represented",At,V,ue,Ut,je,Qn="The offsets associated to each token",Wt,He,Rn=`These offsets let’s you slice the input string, and thus retrieve the original | |
| part that led to producing the corresponding token.`,Ft,L,me,Jt,Ve,On='A <code>List</code> of overflowing <a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a>',Nt,Ge,Yn=`When using truncation, the <a href="/docs/tokenizers/pr_2049/en/api/tokenizer#tokenizers.Tokenizer">Tokenizer</a> takes care of splitting | |
| the output into as many pieces as required to match the specified maximum length. | |
| This field lets you retrieve all the subsequent pieces.`,Bt,Se,Kn=`When you use pairs of sequences, the overflowing pieces will contain enough | |
| variations to cover all the possible combinations, while respecting the provided | |
| maximum length.`,Xt,G,he,Qt,Ze,er="The generated sequence indices.",Rt,Ae,tr=`They represent the index of the input sequence associated to each token. | |
| The sequence id can be None if the token is not related to any input sequence, | |
| like for example with special tokens.`,Ot,S,ge,Yt,Ue,nr="The special token mask",Kt,We,rr="This indicates which tokens are special tokens, and which are not.",en,Z,fe,tn,Fe,or="The generated tokens",nn,Je,sr="They are the string representation of the IDs.",rn,A,xe,on,Ne,ir="The generated type IDs",sn,Be,ar=`Generally used for tasks like sequence classification or question answering, | |
| these tokens let the LM know which input sequence corresponds to each tokens.`,an,I,$e,dn,Xe,dr="The generated word indices.",cn,Qe,cr=`They represent the index of the word associated to each token. | |
| When the input is pre-tokenized, they correspond to the ID of the given input label, | |
| otherwise they correspond to the words indices as defined by the | |
| <a href="/docs/tokenizers/pr_2049/en/api/pre-tokenizers#tokenizers.pre_tokenizers.PreTokenizer">PreTokenizer</a> that was used.`,pn,Re,pr=`For special tokens and such (any token that was generated from something that was | |
| not part of the input), the output is <code>None</code>`,ln,M,_e,un,Oe,lr="The generated word indices.",mn,ee,hn,Ye,ur=`They represent the index of the word associated to each token. | |
| When the input is pre-tokenized, they correspond to the ID of the given input label, | |
| otherwise they correspond to the words indices as defined by the | |
| <a href="/docs/tokenizers/pr_2049/en/api/pre-tokenizers#tokenizers.pre_tokenizers.PreTokenizer">PreTokenizer</a> that was used.`,gn,Ke,mr=`For special tokens and such (any token that was generated from something that was | |
| not part of the input), the output is <code>None</code>`,fn,te,ve,xn,et,hr="Get the token that contains the char at the given position in the input sequence.",$n,ne,ke,_n,tt,gr="Get the word that contains the char at the given position in the input sequence.",vn,re,be,kn,nt,fr='Merge the list of encodings into one final <a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a>',bn,oe,Te,Tn,rt,xr='Pad the <a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a> at the given length',wn,U,we,zn,ot,$r="Set the given sequence index",En,st,_r=`Set the given sequence index for the whole range of tokens contained in this | |
| <a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a>.`,Cn,W,ze,yn,it,vr="Get the offsets of the token at the given index.",qn,at,kr=`The returned offsets are related to the input sequence that contains the | |
| token. In order to determine in which input sequence it belongs, you | |
| must call <code>~tokenizers.Encoding.token_to_sequence()</code>.`,Dn,F,Ee,Mn,dt,br="Get the index of the sequence represented by the given token.",Pn,ct,Tr=`In the general use case, this method returns <code>0</code> for a single sequence or | |
| the first sequence of a pair, and <code>1</code> for the second sequence of a pair`,Ln,J,Ce,In,pt,wr="Get the index of the word that contains the token in one of the input sequences.",jn,lt,zr=`The returned word index is related to the input sequence that contains | |
| the token. In order to determine in which input sequence it belongs, you | |
| must call <code>~tokenizers.Encoding.token_to_sequence()</code>.`,Hn,N,ye,Vn,ut,Er='Truncate the <a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a> at the given length',Gn,mt,Cr=`If this <a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a> represents multiple sequences, when truncating | |
| this information is lost. It will be considered as representing a single sequence.`,Sn,se,qe,Zn,ht,yr="Get the offsets of the word at the given index in one of the input sequences.",An,ie,De,Un,gt,qr=`Get the encoded tokens corresponding to the word at the given index | |
| in one of the input sequences.`,Et;return n=new Dr({props:{title:"Encoding",local:"tokenizers.Encoding",headingTag:"h2"}}),u=new w({props:{name:"class tokenizers.Encoding",anchor:"tokenizers.Encoding",parameters:[]}}),P=new Ar({props:{anchor:"tokenizers.Encoding.example",$$slots:{default:[Ur]},$$scope:{ctx:E}}}),c=new w({props:{name:"attention_mask",anchor:"tokenizers.Encoding.attention_mask",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The attention mask</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>List[int]</code></p> | |
| `,isGetSetDescriptor:!0}}),pe=new w({props:{name:"ids",anchor:"tokenizers.Encoding.ids",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The list of IDs</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>List[int]</code></p> | |
| `,isGetSetDescriptor:!0}}),le=new w({props:{name:"n_sequences",anchor:"tokenizers.Encoding.n_sequences",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The number of sequences in this <a | |
| href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding" | |
| >Encoding</a></p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>int</code></p> | |
| `,isGetSetDescriptor:!0}}),ue=new w({props:{name:"offsets",anchor:"tokenizers.Encoding.offsets",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The list of offsets</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>A <code>List</code> of <code>Tuple[int, int]</code></p> | |
| `,isGetSetDescriptor:!0}}),me=new w({props:{name:"overflowing",anchor:"tokenizers.Encoding.overflowing",parameters:[],isGetSetDescriptor:!0}}),he=new w({props:{name:"sequence_ids",anchor:"tokenizers.Encoding.sequence_ids",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>A list of optional sequence index.</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>A <code>List</code> of <code>Optional[int]</code></p> | |
| `,isGetSetDescriptor:!0}}),ge=new w({props:{name:"special_tokens_mask",anchor:"tokenizers.Encoding.special_tokens_mask",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The special tokens mask</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>List[int]</code></p> | |
| `,isGetSetDescriptor:!0}}),fe=new w({props:{name:"tokens",anchor:"tokenizers.Encoding.tokens",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The list of tokens</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>List[str]</code></p> | |
| `,isGetSetDescriptor:!0}}),xe=new w({props:{name:"type_ids",anchor:"tokenizers.Encoding.type_ids",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The list of type ids</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>List[int]</code></p> | |
| `,isGetSetDescriptor:!0}}),$e=new w({props:{name:"word_ids",anchor:"tokenizers.Encoding.word_ids",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>A list of optional word index.</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>A <code>List</code> of <code>Optional[int]</code></p> | |
| `,isGetSetDescriptor:!0}}),_e=new w({props:{name:"words",anchor:"tokenizers.Encoding.words",parameters:[],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>A list of optional word index.</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>A <code>List</code> of <code>Optional[int]</code></p> | |
| `,isGetSetDescriptor:!0}}),ee=new Hr({props:{warning:!0,$$slots:{default:[Wr]},$$scope:{ctx:E}}}),ve=new w({props:{name:"char_to_token",anchor:"tokenizers.Encoding.char_to_token",parameters:[{name:"char_pos",val:""},{name:"sequence_index",val:" = 0"}],parametersDescription:[{anchor:"tokenizers.Encoding.char_to_token.char_pos",description:`<strong>char_pos</strong> (<code>int</code>) — | |
| The position of a char in the input string`,name:"char_pos"},{anchor:"tokenizers.Encoding.char_to_token.sequence_index",description:`<strong>sequence_index</strong> (<code>int</code>, defaults to <code>0</code>) — | |
| The index of the sequence that contains the target char`,name:"sequence_index"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The index of the token that contains this char in the encoded sequence</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>int</code></p> | |
| `}}),ke=new w({props:{name:"char_to_word",anchor:"tokenizers.Encoding.char_to_word",parameters:[{name:"char_pos",val:""},{name:"sequence_index",val:" = 0"}],parametersDescription:[{anchor:"tokenizers.Encoding.char_to_word.char_pos",description:`<strong>char_pos</strong> (<code>int</code>) — | |
| The position of a char in the input string`,name:"char_pos"},{anchor:"tokenizers.Encoding.char_to_word.sequence_index",description:`<strong>sequence_index</strong> (<code>int</code>, defaults to <code>0</code>) — | |
| The index of the sequence that contains the target char`,name:"sequence_index"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The index of the word that contains this char in the input sequence</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>int</code></p> | |
| `}}),be=new w({props:{name:"merge",anchor:"tokenizers.Encoding.merge",parameters:[{name:"encodings",val:""},{name:"growing_offsets",val:" = True"}],parametersDescription:[{anchor:"tokenizers.Encoding.merge.encodings",description:`<strong>encodings</strong> (A <code>List</code> of <a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a>) — | |
| The list of encodings that should be merged in one`,name:"encodings"},{anchor:"tokenizers.Encoding.merge.growing_offsets",description:`<strong>growing_offsets</strong> (<code>bool</code>, defaults to <code>True</code>) — | |
| Whether the offsets should accumulate while merging`,name:"growing_offsets"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The resulting Encoding</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><a href="/docs/tokenizers/pr_2049/en/api/encoding#tokenizers.Encoding">Encoding</a></p> | |
| `}}),Te=new w({props:{name:"pad",anchor:"tokenizers.Encoding.pad",parameters:[{name:"length",val:""},{name:"direction",val:" = 'right'"},{name:"pad_id",val:" = 0"},{name:"pad_type_id",val:" = 0"},{name:"pad_token",val:" = '[PAD]'"}],parametersDescription:[{anchor:"tokenizers.Encoding.pad.length",description:`<strong>length</strong> (<code>int</code>) — | |
| The desired length`,name:"length"},{anchor:"tokenizers.Encoding.pad.direction",description:`<strong>direction</strong> — (<code>str</code>, defaults to <code>right</code>): | |
| The expected padding direction. Can be either <code>right</code> or <code>left</code>`,name:"direction"},{anchor:"tokenizers.Encoding.pad.pad_id",description:`<strong>pad_id</strong> (<code>int</code>, defaults to <code>0</code>) — | |
| The ID corresponding to the padding token`,name:"pad_id"},{anchor:"tokenizers.Encoding.pad.pad_type_id",description:`<strong>pad_type_id</strong> (<code>int</code>, defaults to <code>0</code>) — | |
| The type ID corresponding to the padding token`,name:"pad_type_id"},{anchor:"tokenizers.Encoding.pad.pad_token",description:`<strong>pad_token</strong> (<code>str</code>, defaults to <em>[PAD]</em>) — | |
| The pad token to use`,name:"pad_token"}]}}),we=new w({props:{name:"set_sequence_id",anchor:"tokenizers.Encoding.set_sequence_id",parameters:[{name:"sequence_id",val:""}]}}),ze=new w({props:{name:"token_to_chars",anchor:"tokenizers.Encoding.token_to_chars",parameters:[{name:"token_index",val:""}],parametersDescription:[{anchor:"tokenizers.Encoding.token_to_chars.token_index",description:`<strong>token_index</strong> (<code>int</code>) — | |
| The index of a token in the encoded sequence.`,name:"token_index"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The token offsets <code>(first, last + 1)</code></p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>Tuple[int, int]</code></p> | |
| `}}),Ee=new w({props:{name:"token_to_sequence",anchor:"tokenizers.Encoding.token_to_sequence",parameters:[{name:"token_index",val:""}],parametersDescription:[{anchor:"tokenizers.Encoding.token_to_sequence.token_index",description:`<strong>token_index</strong> (<code>int</code>) — | |
| The index of a token in the encoded sequence.`,name:"token_index"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The sequence id of the given token</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>int</code></p> | |
| `}}),Ce=new w({props:{name:"token_to_word",anchor:"tokenizers.Encoding.token_to_word",parameters:[{name:"token_index",val:""}],parametersDescription:[{anchor:"tokenizers.Encoding.token_to_word.token_index",description:`<strong>token_index</strong> (<code>int</code>) — | |
| The index of a token in the encoded sequence.`,name:"token_index"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The index of the word in the relevant input sequence.</p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>int</code></p> | |
| `}}),ye=new w({props:{name:"truncate",anchor:"tokenizers.Encoding.truncate",parameters:[{name:"max_length",val:""},{name:"stride",val:" = 0"},{name:"direction",val:" = 'right'"}],parametersDescription:[{anchor:"tokenizers.Encoding.truncate.max_length",description:`<strong>max_length</strong> (<code>int</code>) — | |
| The desired length`,name:"max_length"},{anchor:"tokenizers.Encoding.truncate.stride",description:`<strong>stride</strong> (<code>int</code>, defaults to <code>0</code>) — | |
| The length of previous content to be included in each overflowing piece`,name:"stride"},{anchor:"tokenizers.Encoding.truncate.direction",description:`<strong>direction</strong> (<code>str</code>, defaults to <code>right</code>) — | |
| Truncate direction`,name:"direction"}]}}),qe=new w({props:{name:"word_to_chars",anchor:"tokenizers.Encoding.word_to_chars",parameters:[{name:"word_index",val:""},{name:"sequence_index",val:" = 0"}],parametersDescription:[{anchor:"tokenizers.Encoding.word_to_chars.word_index",description:`<strong>word_index</strong> (<code>int</code>) — | |
| The index of a word in one of the input sequences.`,name:"word_index"},{anchor:"tokenizers.Encoding.word_to_chars.sequence_index",description:`<strong>sequence_index</strong> (<code>int</code>, defaults to <code>0</code>) — | |
| The index of the sequence that contains the target word`,name:"sequence_index"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The range of characters (span) <code>(first, last + 1)</code></p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>Tuple[int, int]</code></p> | |
| `}}),De=new w({props:{name:"word_to_tokens",anchor:"tokenizers.Encoding.word_to_tokens",parameters:[{name:"word_index",val:""},{name:"sequence_index",val:" = 0"}],parametersDescription:[{anchor:"tokenizers.Encoding.word_to_tokens.word_index",description:`<strong>word_index</strong> (<code>int</code>) — | |
| The index of a word in one of the input sequences.`,name:"word_index"},{anchor:"tokenizers.Encoding.word_to_tokens.sequence_index",description:`<strong>sequence_index</strong> (<code>int</code>, defaults to <code>0</code>) — | |
| The index of the sequence that contains the target word`,name:"sequence_index"}],returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p>The range of tokens: <code>(first, last + 1)</code></p> | |
| `,returnType:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><code>Tuple[int, int]</code></p> | |
| `}}),{c(){h(n.$$.fragment),m=r(),t=s("div"),h(u.$$.fragment),k=r(),v=s("p"),v.innerHTML=D,Y=r(),C=s("p"),C.innerHTML=ce,j=r(),h(P.$$.fragment),X=r(),y=s("div"),h(c.$$.fragment),z=r(),Q=s("p"),Q.textContent=Fn,jt=r(),Me=s("p"),Me.textContent=Jn,Ht=r(),H=s("div"),h(pe.$$.fragment),Vt=r(),Pe=s("p"),Pe.textContent=Nn,Gt=r(),Le=s("p"),Le.textContent=Bn,St=r(),K=s("div"),h(le.$$.fragment),Zt=r(),Ie=s("p"),Ie.textContent=Xn,At=r(),V=s("div"),h(ue.$$.fragment),Ut=r(),je=s("p"),je.textContent=Qn,Wt=r(),He=s("p"),He.textContent=Rn,Ft=r(),L=s("div"),h(me.$$.fragment),Jt=r(),Ve=s("p"),Ve.innerHTML=On,Nt=r(),Ge=s("p"),Ge.innerHTML=Yn,Bt=r(),Se=s("p"),Se.textContent=Kn,Xt=r(),G=s("div"),h(he.$$.fragment),Qt=r(),Ze=s("p"),Ze.textContent=er,Rt=r(),Ae=s("p"),Ae.textContent=tr,Ot=r(),S=s("div"),h(ge.$$.fragment),Yt=r(),Ue=s("p"),Ue.textContent=nr,Kt=r(),We=s("p"),We.textContent=rr,en=r(),Z=s("div"),h(fe.$$.fragment),tn=r(),Fe=s("p"),Fe.textContent=or,nn=r(),Je=s("p"),Je.textContent=sr,rn=r(),A=s("div"),h(xe.$$.fragment),on=r(),Ne=s("p"),Ne.textContent=ir,sn=r(),Be=s("p"),Be.textContent=ar,an=r(),I=s("div"),h($e.$$.fragment),dn=r(),Xe=s("p"),Xe.textContent=dr,cn=r(),Qe=s("p"),Qe.innerHTML=cr,pn=r(),Re=s("p"),Re.innerHTML=pr,ln=r(),M=s("div"),h(_e.$$.fragment),un=r(),Oe=s("p"),Oe.textContent=lr,mn=r(),h(ee.$$.fragment),hn=r(),Ye=s("p"),Ye.innerHTML=ur,gn=r(),Ke=s("p"),Ke.innerHTML=mr,fn=r(),te=s("div"),h(ve.$$.fragment),xn=r(),et=s("p"),et.textContent=hr,$n=r(),ne=s("div"),h(ke.$$.fragment),_n=r(),tt=s("p"),tt.textContent=gr,vn=r(),re=s("div"),h(be.$$.fragment),kn=r(),nt=s("p"),nt.innerHTML=fr,bn=r(),oe=s("div"),h(Te.$$.fragment),Tn=r(),rt=s("p"),rt.innerHTML=xr,wn=r(),U=s("div"),h(we.$$.fragment),zn=r(),ot=s("p"),ot.textContent=$r,En=r(),st=s("p"),st.innerHTML=_r,Cn=r(),W=s("div"),h(ze.$$.fragment),yn=r(),it=s("p"),it.textContent=vr,qn=r(),at=s("p"),at.innerHTML=kr,Dn=r(),F=s("div"),h(Ee.$$.fragment),Mn=r(),dt=s("p"),dt.textContent=br,Pn=r(),ct=s("p"),ct.innerHTML=Tr,Ln=r(),J=s("div"),h(Ce.$$.fragment),In=r(),pt=s("p"),pt.textContent=wr,jn=r(),lt=s("p"),lt.innerHTML=zr,Hn=r(),N=s("div"),h(ye.$$.fragment),Vn=r(),ut=s("p"),ut.innerHTML=Er,Gn=r(),mt=s("p"),mt.innerHTML=Cr,Sn=r(),se=s("div"),h(qe.$$.fragment),Zn=r(),ht=s("p"),ht.textContent=yr,An=r(),ie=s("div"),h(De.$$.fragment),Un=r(),gt=s("p"),gt.textContent=qr,this.h()},l(a){g(n.$$.fragment,a),m=o(a),t=i(a,"DIV",{class:!0});var d=b(t);g(u.$$.fragment,d),k=o(d),v=i(d,"P",{"data-svelte-h":!0}),p(v)!=="svelte-z2kbek"&&(v.innerHTML=D),Y=o(d),C=i(d,"P",{"data-svelte-h":!0}),p(C)!=="svelte-1qmm8yo"&&(C.innerHTML=ce),j=o(d),g(P.$$.fragment,d),X=o(d),y=i(d,"DIV",{class:!0});var R=b(y);g(c.$$.fragment,R),z=o(R),Q=i(R,"P",{"data-svelte-h":!0}),p(Q)!=="svelte-nafsul"&&(Q.textContent=Fn),jt=o(R),Me=i(R,"P",{"data-svelte-h":!0}),p(Me)!=="svelte-2cl9fs"&&(Me.textContent=Jn),R.forEach(l),Ht=o(d),H=i(d,"DIV",{class:!0});var O=b(H);g(pe.$$.fragment,O),Vt=o(O),Pe=i(O,"P",{"data-svelte-h":!0}),p(Pe)!=="svelte-13hu4qs"&&(Pe.textContent=Nn),Gt=o(O),Le=i(O,"P",{"data-svelte-h":!0}),p(Le)!=="svelte-3xucbe"&&(Le.textContent=Bn),O.forEach(l),St=o(d),K=i(d,"DIV",{class:!0});var Ct=b(K);g(le.$$.fragment,Ct),Zt=o(Ct),Ie=i(Ct,"P",{"data-svelte-h":!0}),p(Ie)!=="svelte-128n7bm"&&(Ie.textContent=Xn),Ct.forEach(l),At=o(d),V=i(d,"DIV",{class:!0});var ft=b(V);g(ue.$$.fragment,ft),Ut=o(ft),je=i(ft,"P",{"data-svelte-h":!0}),p(je)!=="svelte-1jccc0s"&&(je.textContent=Qn),Wt=o(ft),He=i(ft,"P",{"data-svelte-h":!0}),p(He)!=="svelte-rqkny6"&&(He.textContent=Rn),ft.forEach(l),Ft=o(d),L=i(d,"DIV",{class:!0});var ae=b(L);g(me.$$.fragment,ae),Jt=o(ae),Ve=i(ae,"P",{"data-svelte-h":!0}),p(Ve)!=="svelte-1f6mthi"&&(Ve.innerHTML=On),Nt=o(ae),Ge=i(ae,"P",{"data-svelte-h":!0}),p(Ge)!=="svelte-1pajss8"&&(Ge.innerHTML=Yn),Bt=o(ae),Se=i(ae,"P",{"data-svelte-h":!0}),p(Se)!=="svelte-77thau"&&(Se.textContent=Kn),ae.forEach(l),Xt=o(d),G=i(d,"DIV",{class:!0});var xt=b(G);g(he.$$.fragment,xt),Qt=o(xt),Ze=i(xt,"P",{"data-svelte-h":!0}),p(Ze)!=="svelte-olyk0g"&&(Ze.textContent=er),Rt=o(xt),Ae=i(xt,"P",{"data-svelte-h":!0}),p(Ae)!=="svelte-1w4yrxp"&&(Ae.textContent=tr),xt.forEach(l),Ot=o(d),S=i(d,"DIV",{class:!0});var $t=b(S);g(ge.$$.fragment,$t),Yt=o($t),Ue=i($t,"P",{"data-svelte-h":!0}),p(Ue)!=="svelte-1kqf199"&&(Ue.textContent=nr),Kt=o($t),We=i($t,"P",{"data-svelte-h":!0}),p(We)!=="svelte-1vxwt8f"&&(We.textContent=rr),$t.forEach(l),en=o(d),Z=i(d,"DIV",{class:!0});var _t=b(Z);g(fe.$$.fragment,_t),tn=o(_t),Fe=i(_t,"P",{"data-svelte-h":!0}),p(Fe)!=="svelte-10jm6aw"&&(Fe.textContent=or),nn=o(_t),Je=i(_t,"P",{"data-svelte-h":!0}),p(Je)!=="svelte-d380jx"&&(Je.textContent=sr),_t.forEach(l),rn=o(d),A=i(d,"DIV",{class:!0});var vt=b(A);g(xe.$$.fragment,vt),on=o(vt),Ne=i(vt,"P",{"data-svelte-h":!0}),p(Ne)!=="svelte-1q6qddw"&&(Ne.textContent=ir),sn=o(vt),Be=i(vt,"P",{"data-svelte-h":!0}),p(Be)!=="svelte-r57n1l"&&(Be.textContent=ar),vt.forEach(l),an=o(d),I=i(d,"DIV",{class:!0});var de=b(I);g($e.$$.fragment,de),dn=o(de),Xe=i(de,"P",{"data-svelte-h":!0}),p(Xe)!=="svelte-7pgnnj"&&(Xe.textContent=dr),cn=o(de),Qe=i(de,"P",{"data-svelte-h":!0}),p(Qe)!=="svelte-f7npf0"&&(Qe.innerHTML=cr),pn=o(de),Re=i(de,"P",{"data-svelte-h":!0}),p(Re)!=="svelte-o7jdc6"&&(Re.innerHTML=pr),de.forEach(l),ln=o(d),M=i(d,"DIV",{class:!0});var B=b(M);g(_e.$$.fragment,B),un=o(B),Oe=i(B,"P",{"data-svelte-h":!0}),p(Oe)!=="svelte-7pgnnj"&&(Oe.textContent=lr),mn=o(B),g(ee.$$.fragment,B),hn=o(B),Ye=i(B,"P",{"data-svelte-h":!0}),p(Ye)!=="svelte-f7npf0"&&(Ye.innerHTML=ur),gn=o(B),Ke=i(B,"P",{"data-svelte-h":!0}),p(Ke)!=="svelte-o7jdc6"&&(Ke.innerHTML=mr),B.forEach(l),fn=o(d),te=i(d,"DIV",{class:!0});var yt=b(te);g(ve.$$.fragment,yt),xn=o(yt),et=i(yt,"P",{"data-svelte-h":!0}),p(et)!=="svelte-1ffrb0"&&(et.textContent=hr),yt.forEach(l),$n=o(d),ne=i(d,"DIV",{class:!0});var qt=b(ne);g(ke.$$.fragment,qt),_n=o(qt),tt=i(qt,"P",{"data-svelte-h":!0}),p(tt)!=="svelte-1ykgp61"&&(tt.textContent=gr),qt.forEach(l),vn=o(d),re=i(d,"DIV",{class:!0});var Dt=b(re);g(be.$$.fragment,Dt),kn=o(Dt),nt=i(Dt,"P",{"data-svelte-h":!0}),p(nt)!=="svelte-19r1aq3"&&(nt.innerHTML=fr),Dt.forEach(l),bn=o(d),oe=i(d,"DIV",{class:!0});var Mt=b(oe);g(Te.$$.fragment,Mt),Tn=o(Mt),rt=i(Mt,"P",{"data-svelte-h":!0}),p(rt)!=="svelte-1tbd8n6"&&(rt.innerHTML=xr),Mt.forEach(l),wn=o(d),U=i(d,"DIV",{class:!0});var kt=b(U);g(we.$$.fragment,kt),zn=o(kt),ot=i(kt,"P",{"data-svelte-h":!0}),p(ot)!=="svelte-1k2furt"&&(ot.textContent=$r),En=o(kt),st=i(kt,"P",{"data-svelte-h":!0}),p(st)!=="svelte-zc653d"&&(st.innerHTML=_r),kt.forEach(l),Cn=o(d),W=i(d,"DIV",{class:!0});var bt=b(W);g(ze.$$.fragment,bt),yn=o(bt),it=i(bt,"P",{"data-svelte-h":!0}),p(it)!=="svelte-1ax7nb7"&&(it.textContent=vr),qn=o(bt),at=i(bt,"P",{"data-svelte-h":!0}),p(at)!=="svelte-rntbkv"&&(at.innerHTML=kr),bt.forEach(l),Dn=o(d),F=i(d,"DIV",{class:!0});var Tt=b(F);g(Ee.$$.fragment,Tt),Mn=o(Tt),dt=i(Tt,"P",{"data-svelte-h":!0}),p(dt)!=="svelte-gsdag5"&&(dt.textContent=br),Pn=o(Tt),ct=i(Tt,"P",{"data-svelte-h":!0}),p(ct)!=="svelte-s4bu5e"&&(ct.innerHTML=Tr),Tt.forEach(l),Ln=o(d),J=i(d,"DIV",{class:!0});var wt=b(J);g(Ce.$$.fragment,wt),In=o(wt),pt=i(wt,"P",{"data-svelte-h":!0}),p(pt)!=="svelte-r4v2i2"&&(pt.textContent=wr),jn=o(wt),lt=i(wt,"P",{"data-svelte-h":!0}),p(lt)!=="svelte-10g7eg5"&&(lt.innerHTML=zr),wt.forEach(l),Hn=o(d),N=i(d,"DIV",{class:!0});var zt=b(N);g(ye.$$.fragment,zt),Vn=o(zt),ut=i(zt,"P",{"data-svelte-h":!0}),p(ut)!=="svelte-1579b7n"&&(ut.innerHTML=Er),Gn=o(zt),mt=i(zt,"P",{"data-svelte-h":!0}),p(mt)!=="svelte-lpda5a"&&(mt.innerHTML=Cr),zt.forEach(l),Sn=o(d),se=i(d,"DIV",{class:!0});var Pt=b(se);g(qe.$$.fragment,Pt),Zn=o(Pt),ht=i(Pt,"P",{"data-svelte-h":!0}),p(ht)!=="svelte-ftg3o5"&&(ht.textContent=yr),Pt.forEach(l),An=o(d),ie=i(d,"DIV",{class:!0});var Lt=b(ie);g(De.$$.fragment,Lt),Un=o(Lt),gt=i(Lt,"P",{"data-svelte-h":!0}),p(gt)!=="svelte-17aw0gq"&&(gt.textContent=qr),Lt.forEach(l),d.forEach(l),this.h()},h(){T(y,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(H,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(K,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(V,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(L,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(G,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(S,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(Z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(A,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(I,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(M,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(te,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(ne,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(re,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(oe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(U,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(W,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(F,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(J,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(N,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(se,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(ie,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(t,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(a,d){f(n,a,d),q(a,m,d),q(a,t,d),f(u,t,null),e(t,k),e(t,v),e(t,Y),e(t,C),e(t,j),f(P,t,null),e(t,X),e(t,y),f(c,y,null),e(y,z),e(y,Q),e(y,jt),e(y,Me),e(t,Ht),e(t,H),f(pe,H,null),e(H,Vt),e(H,Pe),e(H,Gt),e(H,Le),e(t,St),e(t,K),f(le,K,null),e(K,Zt),e(K,Ie),e(t,At),e(t,V),f(ue,V,null),e(V,Ut),e(V,je),e(V,Wt),e(V,He),e(t,Ft),e(t,L),f(me,L,null),e(L,Jt),e(L,Ve),e(L,Nt),e(L,Ge),e(L,Bt),e(L,Se),e(t,Xt),e(t,G),f(he,G,null),e(G,Qt),e(G,Ze),e(G,Rt),e(G,Ae),e(t,Ot),e(t,S),f(ge,S,null),e(S,Yt),e(S,Ue),e(S,Kt),e(S,We),e(t,en),e(t,Z),f(fe,Z,null),e(Z,tn),e(Z,Fe),e(Z,nn),e(Z,Je),e(t,rn),e(t,A),f(xe,A,null),e(A,on),e(A,Ne),e(A,sn),e(A,Be),e(t,an),e(t,I),f($e,I,null),e(I,dn),e(I,Xe),e(I,cn),e(I,Qe),e(I,pn),e(I,Re),e(t,ln),e(t,M),f(_e,M,null),e(M,un),e(M,Oe),e(M,mn),f(ee,M,null),e(M,hn),e(M,Ye),e(M,gn),e(M,Ke),e(t,fn),e(t,te),f(ve,te,null),e(te,xn),e(te,et),e(t,$n),e(t,ne),f(ke,ne,null),e(ne,_n),e(ne,tt),e(t,vn),e(t,re),f(be,re,null),e(re,kn),e(re,nt),e(t,bn),e(t,oe),f(Te,oe,null),e(oe,Tn),e(oe,rt),e(t,wn),e(t,U),f(we,U,null),e(U,zn),e(U,ot),e(U,En),e(U,st),e(t,Cn),e(t,W),f(ze,W,null),e(W,yn),e(W,it),e(W,qn),e(W,at),e(t,Dn),e(t,F),f(Ee,F,null),e(F,Mn),e(F,dt),e(F,Pn),e(F,ct),e(t,Ln),e(t,J),f(Ce,J,null),e(J,In),e(J,pt),e(J,jn),e(J,lt),e(t,Hn),e(t,N),f(ye,N,null),e(N,Vn),e(N,ut),e(N,Gn),e(N,mt),e(t,Sn),e(t,se),f(qe,se,null),e(se,Zn),e(se,ht),e(t,An),e(t,ie),f(De,ie,null),e(ie,Un),e(ie,gt),Et=!0},p(a,d){const R={};d&2&&(R.$$scope={dirty:d,ctx:a}),P.$set(R);const O={};d&2&&(O.$$scope={dirty:d,ctx:a}),ee.$set(O)},i(a){Et||(x(n.$$.fragment,a),x(u.$$.fragment,a),x(P.$$.fragment,a),x(c.$$.fragment,a),x(pe.$$.fragment,a),x(le.$$.fragment,a),x(ue.$$.fragment,a),x(me.$$.fragment,a),x(he.$$.fragment,a),x(ge.$$.fragment,a),x(fe.$$.fragment,a),x(xe.$$.fragment,a),x($e.$$.fragment,a),x(_e.$$.fragment,a),x(ee.$$.fragment,a),x(ve.$$.fragment,a),x(ke.$$.fragment,a),x(be.$$.fragment,a),x(Te.$$.fragment,a),x(we.$$.fragment,a),x(ze.$$.fragment,a),x(Ee.$$.fragment,a),x(Ce.$$.fragment,a),x(ye.$$.fragment,a),x(qe.$$.fragment,a),x(De.$$.fragment,a),Et=!0)},o(a){$(n.$$.fragment,a),$(u.$$.fragment,a),$(P.$$.fragment,a),$(c.$$.fragment,a),$(pe.$$.fragment,a),$(le.$$.fragment,a),$(ue.$$.fragment,a),$(me.$$.fragment,a),$(he.$$.fragment,a),$(ge.$$.fragment,a),$(fe.$$.fragment,a),$(xe.$$.fragment,a),$($e.$$.fragment,a),$(_e.$$.fragment,a),$(ee.$$.fragment,a),$(ve.$$.fragment,a),$(ke.$$.fragment,a),$(be.$$.fragment,a),$(Te.$$.fragment,a),$(we.$$.fragment,a),$(ze.$$.fragment,a),$(Ee.$$.fragment,a),$(Ce.$$.fragment,a),$(ye.$$.fragment,a),$(qe.$$.fragment,a),$(De.$$.fragment,a),Et=!1},d(a){a&&(l(m),l(t)),_(n,a),_(u),_(P),_(c),_(pe),_(le),_(ue),_(me),_(he),_(ge),_(fe),_(xe),_($e),_(_e),_(ee),_(ve),_(ke),_(be),_(Te),_(we),_(ze),_(Ee),_(Ce),_(ye),_(qe),_(De)}}}function Jr(E){let n,m;return n=new Wn({props:{$$slots:{default:[Fr]},$$scope:{ctx:E}}}),{c(){h(n.$$.fragment)},l(t){g(n.$$.fragment,t)},m(t,u){f(n,t,u),m=!0},p(t,u){const k={};u&2&&(k.$$scope={dirty:u,ctx:t}),n.$set(k)},i(t){m||(x(n.$$.fragment,t),m=!0)},o(t){$(n.$$.fragment,t),m=!1},d(t){_(n,t)}}}function Nr(E){let n,m='The Rust API Reference is available directly on the <a href="https://docs.rs/tokenizers/latest/tokenizers/" rel="nofollow">Docs.rs</a> website.';return{c(){n=s("p"),n.innerHTML=m},l(t){n=i(t,"P",{"data-svelte-h":!0}),p(n)!=="svelte-4ytcyb"&&(n.innerHTML=m)},m(t,u){q(t,n,u)},p:It,d(t){t&&l(n)}}}function Br(E){let n,m;return n=new Wn({props:{$$slots:{default:[Nr]},$$scope:{ctx:E}}}),{c(){h(n.$$.fragment)},l(t){g(n.$$.fragment,t)},m(t,u){f(n,t,u),m=!0},p(t,u){const k={};u&2&&(k.$$scope={dirty:u,ctx:t}),n.$set(k)},i(t){m||(x(n.$$.fragment,t),m=!0)},o(t){$(n.$$.fragment,t),m=!1},d(t){_(n,t)}}}function Xr(E){let n,m="The node API has not been documented yet.";return{c(){n=s("p"),n.textContent=m},l(t){n=i(t,"P",{"data-svelte-h":!0}),p(n)!=="svelte-1mrchm6"&&(n.textContent=m)},m(t,u){q(t,n,u)},p:It,d(t){t&&l(n)}}}function Qr(E){let n,m;return n=new Wn({props:{$$slots:{default:[Xr]},$$scope:{ctx:E}}}),{c(){h(n.$$.fragment)},l(t){g(n.$$.fragment,t)},m(t,u){f(n,t,u),m=!0},p(t,u){const k={};u&2&&(k.$$scope={dirty:u,ctx:t}),n.$set(k)},i(t){m||(x(n.$$.fragment,t),m=!0)},o(t){$(n.$$.fragment,t),m=!1},d(t){_(n,t)}}}function Rr(E){let n,m,t,u,k,v,D,Y,C,ce,j,P,X,y;return k=new Vr({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),D=new Dr({props:{title:"Encoding",local:"encoding",headingTag:"h1"}}),C=new Zr({props:{python:!0,rust:!0,node:!0,$$slots:{node:[Qr],rust:[Br],python:[Jr]},$$scope:{ctx:E}}}),j=new Gr({props:{source:"https://github.com/huggingface/tokenizers/blob/main/docs/source-doc-builder/api/encoding.mdx"}}),{c(){n=s("meta"),m=r(),t=s("p"),u=r(),h(k.$$.fragment),v=r(),h(D.$$.fragment),Y=r(),h(C.$$.fragment),ce=r(),h(j.$$.fragment),P=r(),X=s("p"),this.h()},l(c){const z=jr("svelte-u9bgzb",document.head);n=i(z,"META",{name:!0,content:!0}),z.forEach(l),m=o(c),t=i(c,"P",{}),b(t).forEach(l),u=o(c),g(k.$$.fragment,c),v=o(c),g(D.$$.fragment,c),Y=o(c),g(C.$$.fragment,c),ce=o(c),g(j.$$.fragment,c),P=o(c),X=i(c,"P",{}),b(X).forEach(l),this.h()},h(){T(n,"name","hf:doc:metadata"),T(n,"content",Or)},m(c,z){e(document.head,n),q(c,m,z),q(c,t,z),q(c,u,z),f(k,c,z),q(c,v,z),f(D,c,z),q(c,Y,z),f(C,c,z),q(c,ce,z),f(j,c,z),q(c,P,z),q(c,X,z),y=!0},p(c,[z]){const Q={};z&2&&(Q.$$scope={dirty:z,ctx:c}),C.$set(Q)},i(c){y||(x(k.$$.fragment,c),x(D.$$.fragment,c),x(C.$$.fragment,c),x(j.$$.fragment,c),y=!0)},o(c){$(k.$$.fragment,c),$(D.$$.fragment,c),$(C.$$.fragment,c),$(j.$$.fragment,c),y=!1},d(c){c&&(l(m),l(t),l(u),l(v),l(Y),l(ce),l(P),l(X)),l(n),_(k,c),_(D,c),_(C,c),_(j,c)}}}const Or='{"title":"Encoding","local":"encoding","sections":[{"title":"Encoding","local":"tokenizers.Encoding","sections":[],"depth":2}],"depth":1}';function Yr(E){return Pr(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ao extends Lr{constructor(n){super(),Ir(this,n,Yr,Rr,Mr,{})}}export{ao as component}; | |
Xet Storage Details
- Size:
- 37.8 kB
- Xet hash:
- 942c61a20cd710198a834ee4c7567ba500fefd93ec8f24643b71cc02bcfb864b
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.