Buckets:

hf-doc-build
/

doc-dev

hf-doc-build/doc-dev / optimum-intel /pr_1684 /en /_app /immutable /nodes /8.112bfdfd.js

HuggingFaceDocBuilder's picture

HuggingFaceDocBuilder

about 1 month ago

232 kB

	import{s as el,n as q,o as lr,h as Nd,i as Wd,r as qd,t as Rd,e as Gd,c as Ld,u as Ed,g as Pd,a as Hd}from"../chunks/scheduler.78014155.js";import{S as tl,i as nl,w as nn,m as h,d as l,e as g,H as ht,a as f,f as Z,C as vt,k as C,q as Aa,s as r,c as _,b as d,g as M,l as i,n as w,B as Ys,t as b,y as Hs,o as y,x as Qs,p as $,j as F,A as ol,r as en,u as tn,D as Xd,v as Ka,E as zd,h as Qd}from"../chunks/index.931289e0.js";import{T as le}from"../chunks/Tip.1eb6ac6f.js";import{aL as sl,aM as Sd,C as Yd,H as G}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.baeea378.js";import{e as on}from"../chunks/each.e59479a4.js";import{C as D}from"../chunks/CodeBlock.758c56e1.js";function gd(p){let t,a,o;return{c(){t=g("div"),a=new ht(!1),this.h()},l(s){t=f(s,"DIV",{class:!0,style:!0,id:!0});var m=Z(t);a=vt(m,!1),m.forEach(l),this.h()},h(){a.a=null,C(t,"class",o="absolute text-base py-1.5 p-2 break-words bg-white border-2 border-black dark:border-gray-500 rounded shadow-alternate-xl z-50 "+(p[0].length>1e3?"max-w-lg":"max-w-xs")),Aa(t,"top",p[2]+15+"px"),Aa(t,"left",p[1]+15+"px"),C(t,"id",p[3])},m(s,m){h(s,t,m),a.m(p[0],t)},p(s,m){m&1&&a.p(s[0]),m&1&&o!==(o="absolute text-base py-1.5 p-2 break-words bg-white border-2 border-black dark:border-gray-500 rounded shadow-alternate-xl z-50 "+(s[0].length>1e3?"max-w-lg":"max-w-xs"))&&C(t,"class",o),m&4&&Aa(t,"top",s[2]+15+"px"),m&2&&Aa(t,"left",s[1]+15+"px"),m&8&&C(t,"id",s[3])},d(s){s&&l(t)}}}function Dd(p){let t,a=p[0]&&gd(p);return{c(){a&&a.c(),t=nn()},l(o){a&&a.l(o),t=nn()},m(o,s){a&&a.m(o,s),h(o,t,s)},p(o,[s]){o[0]?a?a.p(o,s):(a=gd(o),a.c(),a.m(t.parentNode,t)):a&&(a.d(1),a=null)},i:q,o:q,d(o){o&&l(t),a&&a.d(o)}}}function Ad(p,t,a){let{txt:o}=t,{x:s}=t,{y:m}=t,{id:n}=t;return p.$$set=c=>{"txt"in c&&a(0,o=c.txt),"x"in c&&a(1,s=c.x),"y"in c&&a(2,m=c.y),"id"in c&&a(3,n=c.id)},[o,s,m,n]}class Kd extends tl{constructor(t){super(),nl(this,t,Ad,Dd,el,{txt:0,x:1,y:2,id:3})}}const fd="docstring-tooltip";function Bd(p,t){let a;function o(c){n(),a=new Kd({props:{txt:t,x:c.pageX,y:c.pageY,id:fd},target:document.body})}function s(c){a.$set({x:c.pageX,y:c.pageY})}function m(){a.$destroy()}function n(){var x;const c=document.getElementById(fd);c&&((x=c.parentNode)==null\|\|x.removeChild(c))}return p.addEventListener("mouseover",o),p.addEventListener("mouseleave",m),p.addEventListener("mousemove",s),{destroy(){p.removeEventListener("mouseover",o),p.removeEventListener("mouseleave",m),p.removeEventListener("mousemove",s)}}}const{window:ec}=Sd;function hd(p,t,a){const o=p.slice();return o[26]=t[a].title,o[11]=t[a].parametersDescription,o}function vd(p,t,a){const o=p.slice();return o[9]=t[a].anchor,o[29]=t[a].description,o}function bd(p,t,a){const o=p.slice();return o[9]=t[a].anchor,o[29]=t[a].description,o}function yd(p,t,a){const o=p.slice();return o[10]=t[a].name,o[34]=t[a].val,o}function _d(p){let t,a,o="<",s,m,n="source",c,x,J=">";return{c(){t=g("a"),a=g("span"),a.textContent=o,s=r(),m=g("span"),m.textContent=n,c=r(),x=g("span"),x.textContent=J,this.h()},l(j){t=f(j,"A",{class:!0,href:!0,target:!0});var v=Z(t);a=f(v,"SPAN",{"data-svelte-h":!0}),F(a)!=="svelte-1kd6by1"&&(a.textContent=o),s=d(v),m=f(v,"SPAN",{class:!0,"data-svelte-h":!0}),F(m)!=="svelte-122apf4"&&(m.textContent=n),c=d(v),x=f(v,"SPAN",{"data-svelte-h":!0}),F(x)!=="svelte-x0xyl0"&&(x.textContent=J),v.forEach(l),this.h()},h(){C(m,"class","hidden md:block mx-0.5 hover:!underline"),C(t,"class","!ml-auto !text-gray-400 !no-underline text-sm flex items-center"),C(t,"href",p[7]),C(t,"target","_blank")},m(j,v){h(j,t,v),i(t,a),i(t,s),i(t,m),i(t,c),i(t,x)},p(j,v){v[0]&128&&C(t,"href",j[7])},d(j){j&&l(t)}}}function Md(p){let t,a,o="(",s,m,n,c=")",x,J=on(p[1]),j=[];for(let k=0;k<J.length;k+=1)j[k]=wd(yd(p,J,k));let v=p[4]&&$d(p);return{c(){t=g("p"),a=g("span"),a.textContent=o,s=r();for(let k=0;k<j.length;k+=1)j[k].c();m=r(),n=g("span"),n.textContent=c,x=r(),v&&v.c(),this.h()},l(k){t=f(k,"P",{class:!0});var V=Z(t);a=f(V,"SPAN",{"data-svelte-h":!0}),F(a)!=="svelte-8mvn6a"&&(a.textContent=o),s=d(V);for(let T=0;T<j.length;T+=1)j[T].l(V);m=d(V),n=f(V,"SPAN",{"data-svelte-h":!0}),F(n)!=="svelte-1jq0pl7"&&(n.textContent=c),x=d(V),v&&v.l(V),V.forEach(l),this.h()},h(){C(t,"class","font-mono text-xs md:text-sm !leading-relaxed !my-6")},m(k,V){h(k,t,V),i(t,a),i(t,s);for(let T=0;T<j.length;T+=1)j[T]&&j[T].m(t,null);i(t,m),i(t,n),i(t,x),v&&v.m(t,null)},p(k,V){if(V[0]&147970){J=on(k[1]);let T;for(T=0;T<J.length;T+=1){const O=yd(k,J,T);j[T]?j[T].p(O,V):(j[T]=wd(O),j[T].c(),j[T].m(t,m))}for(;T<j.length;T+=1)j[T].d(1);j.length=J.length}k[4]?v?v.p(k,V):(v=$d(k),v.c(),v.m(t,null)):v&&(v.d(1),v=null)},d(k){k&&l(t),ol(j,k),v&&v.d()}}}function wd(p){let t,a,o=p[10]+"",s,m,n=p[34]+"",c,x,J,j,v;function k(){return p[21](p[10])}return{c(){t=g("span"),a=g("span"),s=en(o),m=g("span"),c=en(n),this.h()},l(V){t=f(V,"SPAN",{class:!0});var T=Z(t);a=f(T,"SPAN",{class:!0});var O=Z(a);s=tn(O,o),m=f(O,"SPAN",{class:!0});var W=Z(m);c=tn(W,n),W.forEach(l),O.forEach(l),T.forEach(l),this.h()},h(){C(m,"class","opacity-60"),C(a,"class","rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black"),C(t,"class",x="comma "+(p[14][p[10]]?"cursor-pointer":"cursor-default"))},m(V,T){h(V,t,T),i(t,a),i(a,s),i(a,m),i(m,c),j\|\|(v=[Nd(J=Bd.call(null,t,p[14][p[10]]\|\|"")),Ys(t,"click",Xd(zd(k)))],j=!0)},p(V,T){p=V,T[0]&2&&o!==(o=p[10]+"")&&Ka(s,o),T[0]&2&&n!==(n=p[34]+"")&&Ka(c,n),T[0]&2&&x!==(x="comma "+(p[14][p[10]]?"cursor-pointer":"cursor-default"))&&C(t,"class",x),J&&Wd(J.update)&&T[0]&2&&J.update.call(null,p[14][p[10]]\|\|"")},d(V){V&&l(t),j=!1,qd(v)}}}function $d(p){let t,a="→",o,s,m,n=Ud(p[4])+"",c,x,J,j;return{c(){t=g("span"),t.textContent=a,o=r(),s=g("span"),m=new ht(!1),this.h()},l(v){t=f(v,"SPAN",{class:!0,"data-svelte-h":!0}),F(t)!=="svelte-1j6k10o"&&(t.textContent=a),o=d(v),s=f(v,"SPAN",{class:!0});var k=Z(s);m=vt(k,!1),k.forEach(l),this.h()},h(){C(t,"class","font-bold"),m.a=null,C(s,"class",c="rounded hover:bg-gray-400 "+(p[3]?"cursor-pointer":"cursor-default"))},m(v,k){h(v,t,k),h(v,o,k),h(v,s,k),m.m(n,s),J\|\|(j=[Nd(x=Bd.call(null,s,p[3]\|\|"")),Ys(s,"click",Xd(zd(p[22])))],J=!0)},p(v,k){k[0]&16&&n!==(n=Ud(v[4])+"")&&m.p(n),k[0]&8&&c!==(c="rounded hover:bg-gray-400 "+(v[3]?"cursor-pointer":"cursor-default"))&&C(s,"class",c),x&&Wd(x.update)&&k[0]&8&&x.update.call(null,v[3]\|\|"")},d(v){v&&(l(t),l(o),l(s)),J=!1,qd(j)}}}function Td(p){var J;let t,a,o,s=((J=p[11])==null?void 0:J.length)+"",m,n,c,x;return{c(){t=g("div"),a=g("button"),o=en("Expand "),m=en(s),n=en(" parameters"),this.h()},l(j){t=f(j,"DIV",{class:!0});var v=Z(t);a=f(v,"BUTTON",{class:!0});var k=Z(a);o=tn(k,"Expand "),m=tn(k,s),n=tn(k," parameters"),k.forEach(l),v.forEach(l),this.h()},h(){C(a,"class","absolute leading-tight px-3 py-1.5 dark:bg-gray-900 bg-black text-gray-200 hover:text-white rounded-xl bottom-12 ring-offset-2 hover:ring-black hover:ring-2"),C(t,"class","absolute inset-0 bg-gradient-to-t from-white to-white/0 dark:from-gray-950 dark:to-gray-950/0 z-10 flex justify-center")},m(j,v){h(j,t,v),i(t,a),i(a,o),i(a,m),i(a,n),c\|\|(x=Ys(a,"click",p[23]),c=!0)},p(j,v){var k;v[0]&2048&&s!==(s=((k=j[11])==null?void 0:k.length)+"")&&Ka(m,s)},d(j){j&&l(t),c=!1,x()}}}function kd(p){let t,a='Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span>',o,s,m,n=on(p[11]),c=[];for(let J=0;J<n.length;J+=1)c[J]=Vd(bd(p,n,J));const x=J=>y(c[J],1,1,()=>{c[J]=null});return{c(){t=g("p"),t.innerHTML=a,o=r(),s=g("ul");for(let J=0;J<c.length;J+=1)c[J].c();this.h()},l(J){t=f(J,"P",{class:!0,"data-svelte-h":!0}),F(t)!=="svelte-lt6pb6"&&(t.innerHTML=a),o=d(J),s=f(J,"UL",{class:!0});var j=Z(s);for(let v=0;v<c.length;v+=1)c[v].l(j);j.forEach(l),this.h()},h(){C(t,"class","flex items-center font-semibold !mt-2 !mb-2 text-gray-800"),C(s,"class","px-2")},m(J,j){h(J,t,j),h(J,o,j),h(J,s,j);for(let v=0;v<c.length;v+=1)c[v]&&c[v].m(s,null);m=!0},p(J,j){if(j[0]&2049){n=on(J[11]);let v;for(v=0;v<n.length;v+=1){const k=bd(J,n,v);c[v]?(c[v].p(k,j),b(c[v],1)):(c[v]=Vd(k),c[v].c(),b(c[v],1),c[v].m(s,null))}for(Hs(),v=n.length;v<c.length;v+=1)x(v);Qs()}},i(J){if(!m){for(let j=0;j<n.length;j+=1)b(c[j]);m=!0}},o(J){c=c.filter(Boolean);for(let j=0;j<c.length;j+=1)y(c[j]);m=!1},d(J){J&&(l(t),l(o),l(s)),ol(c,J)}}}function Vd(p){let t,a,o,s,m,n,c,x,J,j,v=p[29]+"",k,V,T;return m=new sl({props:{classNames:"text-smd"}}),{c(){t=g("li"),a=g("span"),o=g("a"),s=g("span"),_(m.$$.fragment),x=r(),J=g("span"),j=new ht(!1),k=r(),this.h()},l(O){t=f(O,"LI",{class:!0});var W=Z(t);a=f(W,"SPAN",{class:!0});var z=Z(a);o=f(z,"A",{id:!0,class:!0,href:!0});var S=Z(o);s=f(S,"SPAN",{});var ee=Z(s);M(m.$$.fragment,ee),ee.forEach(l),S.forEach(l),x=d(z),J=f(z,"SPAN",{});var te=Z(J);j=vt(te,!1),te.forEach(l),z.forEach(l),k=d(W),W.forEach(l),this.h()},h(){C(o,"id",n=p[9]),C(o,"class","header-link block pr-0.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),C(o,"href",c=`#${p[9]}`),j.a=null,C(a,"class","group flex space-x-1.5 items-start"),C(t,"class",V="text-base !pl-4 my-3 rounded "+(p[0]===p[9]?sn:""))},m(O,W){h(O,t,W),i(t,a),i(a,o),i(o,s),w(m,s,null),i(a,x),i(a,J),j.m(v,J),i(t,k),T=!0},p(O,W){(!T\|\|W[0]&2048&&n!==(n=O[9]))&&C(o,"id",n),(!T\|\|W[0]&2048&&c!==(c=`#${O[9]}`))&&C(o,"href",c),(!T\|\|W[0]&2048)&&v!==(v=O[29]+"")&&j.p(v),(!T\|\|W[0]&2049&&V!==(V="text-base !pl-4 my-3 rounded "+(O[0]===O[9]?sn:"")))&&C(t,"class",V)},i(O){T\|\|(b(m.$$.fragment,O),T=!0)},o(O){y(m.$$.fragment,O),T=!1},d(O){O&&l(t),$(m)}}}function Cd(p){let t,a,o=on(p[2]),s=[];for(let n=0;n<o.length;n+=1)s[n]=jd(hd(p,o,n));const m=n=>y(s[n],1,1,()=>{s[n]=null});return{c(){for(let n=0;n<s.length;n+=1)s[n].c();t=nn()},l(n){for(let c=0;c<s.length;c+=1)s[c].l(n);t=nn()},m(n,c){for(let x=0;x<s.length;x+=1)s[x]&&s[x].m(n,c);h(n,t,c),a=!0},p(n,c){if(c[0]&5){o=on(n[2]);let x;for(x=0;x<o.length;x+=1){const J=hd(n,o,x);s[x]?(s[x].p(J,c),b(s[x],1)):(s[x]=jd(J),s[x].c(),b(s[x],1),s[x].m(t.parentNode,t))}for(Hs(),x=o.length;x<s.length;x+=1)m(x);Qs()}},i(n){if(!a){for(let c=0;c<o.length;c+=1)b(s[c]);a=!0}},o(n){s=s.filter(Boolean);for(let c=0;c<s.length;c+=1)y(s[c]);a=!1},d(n){n&&l(t),ol(s,n)}}}function Jd(p){let t,a,o,s,m,n,c,x,J,j,v=p[29]+"",k,V;return m=new sl({props:{classNames:"text-smd"}}),{c(){t=g("li"),a=g("span"),o=g("a"),s=g("span"),_(m.$$.fragment),x=r(),J=g("span"),j=new ht(!1),this.h()},l(T){t=f(T,"LI",{class:!0});var O=Z(t);a=f(O,"SPAN",{class:!0});var W=Z(a);o=f(W,"A",{id:!0,class:!0,href:!0});var z=Z(o);s=f(z,"SPAN",{});var S=Z(s);M(m.$$.fragment,S),S.forEach(l),z.forEach(l),x=d(W),J=f(W,"SPAN",{});var ee=Z(J);j=vt(ee,!1),ee.forEach(l),W.forEach(l),O.forEach(l),this.h()},h(){C(o,"id",n=p[9]),C(o,"class","header-link block pr-0.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),C(o,"href",c=`#${p[9]}`),j.a=null,C(a,"class","group flex space-x-1.5 items-start"),C(t,"class",k="text-base !pl-4 my-3 rounded "+(p[0]===p[9]?sn:""))},m(T,O){h(T,t,O),i(t,a),i(a,o),i(o,s),w(m,s,null),i(a,x),i(a,J),j.m(v,J),V=!0},p(T,O){(!V\|\|O[0]&4&&n!==(n=T[9]))&&C(o,"id",n),(!V\|\|O[0]&4&&c!==(c=`#${T[9]}`))&&C(o,"href",c),(!V\|\|O[0]&4)&&v!==(v=T[29]+"")&&j.p(v),(!V\|\|O[0]&5&&k!==(k="text-base !pl-4 my-3 rounded "+(T[0]===T[9]?sn:"")))&&C(t,"class",k)},i(T){V\|\|(b(m.$$.fragment,T),V=!0)},o(T){y(m.$$.fragment,T),V=!1},d(T){T&&l(t),$(m)}}}function jd(p){let t,a=p[26]+"",o,s,m,n,c,x,J,j=on(p[11]),v=[];for(let V=0;V<j.length;V+=1)v[V]=Jd(vd(p,j,V));const k=V=>y(v[V],1,1,()=>{v[V]=null});return{c(){t=g("p"),o=en(a),s=r(),m=g("span"),n=r(),c=g("ul");for(let V=0;V<v.length;V+=1)v[V].c();x=r(),this.h()},l(V){t=f(V,"P",{class:!0});var T=Z(t);o=tn(T,a),s=d(T),m=f(T,"SPAN",{class:!0}),Z(m).forEach(l),T.forEach(l),n=d(V),c=f(V,"UL",{class:!0});var O=Z(c);for(let W=0;W<v.length;W+=1)v[W].l(O);x=d(O),O.forEach(l),this.h()},h(){C(m,"class","flex-auto border-t-2 ml-3"),C(t,"class","flex items-center font-semibold"),C(c,"class","px-2")},m(V,T){h(V,t,T),i(t,o),i(t,s),i(t,m),h(V,n,T),h(V,c,T);for(let O=0;O<v.length;O+=1)v[O]&&v[O].m(c,null);i(c,x),J=!0},p(V,T){if((!J\|\|T[0]&4)&&a!==(a=V[26]+"")&&Ka(o,a),T[0]&5){j=on(V[11]);let O;for(O=0;O<j.length;O+=1){const W=vd(V,j,O);v[O]?(v[O].p(W,T),b(v[O],1)):(v[O]=Jd(W),v[O].c(),b(v[O],1),v[O].m(c,x))}for(Hs(),O=j.length;O<v.length;O+=1)k(O);Qs()}},i(V){if(!J){for(let T=0;T<j.length;T+=1)b(v[T]);J=!0}},o(V){v=v.filter(Boolean);for(let T=0;T<v.length;T+=1)y(v[T]);J=!1},d(V){V&&(l(t),l(n),l(c)),ol(v,V)}}}function Fd(p){let t,a,o,s,m,n,c,x,J,j,v,k=(p[3]\|\|"")+"",V=!!p[4]&&xd(p);return{c(){t=g("div"),a=g("p"),o=en(p[15]),s=r(),V&&V.c(),m=r(),n=g("span"),J=r(),j=g("p"),v=new ht(!1),this.h()},l(T){t=f(T,"DIV",{id:!0,class:!0});var O=Z(t);a=f(O,"P",{class:!0});var W=Z(a);o=tn(W,p[15]),W.forEach(l),s=d(O),V&&V.l(O),m=d(O),n=f(O,"SPAN",{class:!0}),Z(n).forEach(l),O.forEach(l),J=d(T),j=f(T,"P",{class:!0});var z=Z(j);v=vt(z,!1),z.forEach(l),this.h()},h(){C(a,"class","text-base"),C(n,"class","flex-auto border-t-2 border-gray-100 dark:border-gray-700"),C(t,"id",c=`${p[9]}.${p[16]}`),C(t,"class",x="flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800 rounded "+(p[0]===p[9]?sn:"")),v.a=null,C(j,"class","text-base")},m(T,O){h(T,t,O),i(t,a),i(a,o),i(t,s),V&&V.m(t,null),i(t,m),i(t,n),h(T,J,O),h(T,j,O),v.m(k,j)},p(T,O){T[4]?V?V.p(T,O):(V=xd(T),V.c(),V.m(t,m)):V&&(V.d(1),V=null),O[0]&512&&c!==(c=`${T[9]}.${T[16]}`)&&C(t,"id",c),O[0]&513&&x!==(x="flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800 rounded "+(T[0]===T[9]?sn:""))&&C(t,"class",x),O[0]&8&&k!==(k=(T[3]\|\|"")+"")&&v.p(k)},d(T){T&&(l(t),l(J),l(j)),V&&V.d()}}}function xd(p){let t,a;return{c(){t=new ht(!1),a=nn(),this.h()},l(o){t=vt(o,!1),a=nn(),this.h()},h(){t.a=a},m(o,s){t.m(p[4],o,s),h(o,a,s)},p(o,s){s[0]&16&&t.p(o[4])},d(o){o&&(l(a),t.d())}}}function Od(p){let t,a,o="Raises",s,m,n,c,x,J,j,v=(p[5]\|\|"")+"",k=!!p[6]&&Zd(p);return{c(){t=g("div"),a=g("p"),a.textContent=o,s=r(),k&&k.c(),m=r(),n=g("span"),x=r(),J=g("p"),j=new ht(!1),this.h()},l(V){t=f(V,"DIV",{class:!0,id:!0});var T=Z(t);a=f(T,"P",{class:!0,"data-svelte-h":!0}),F(a)!=="svelte-1ak550f"&&(a.textContent=o),s=d(T),k&&k.l(T),m=d(T),n=f(T,"SPAN",{class:!0}),Z(n).forEach(l),T.forEach(l),x=d(V),J=f(V,"P",{class:!0});var O=Z(J);j=vt(O,!1),O.forEach(l),this.h()},h(){C(a,"class","text-base"),C(n,"class","flex-auto border-t-2 border-gray-100 dark:border-gray-700"),C(t,"class","flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800"),C(t,"id",c=`${p[9]}.raises`),j.a=null,C(J,"class","text-base")},m(V,T){h(V,t,T),i(t,a),i(t,s),k&&k.m(t,null),i(t,m),i(t,n),h(V,x,T),h(V,J,T),j.m(v,J)},p(V,T){V[6]?k?k.p(V,T):(k=Zd(V),k.c(),k.m(t,m)):k&&(k.d(1),k=null),T[0]&512&&c!==(c=`${V[9]}.raises`)&&C(t,"id",c),T[0]&32&&v!==(v=(V[5]\|\|"")+"")&&j.p(v)},d(V){V&&(l(t),l(x),l(J)),k&&k.d()}}}function Zd(p){let t,a;return{c(){t=new ht(!1),a=nn(),this.h()},l(o){t=vt(o,!1),a=nn(),this.h()},h(){t.a=a},m(o,s){t.m(p[6],o,s),h(o,a,s)},p(o,s){s[0]&64&&t.p(o[6])},d(o){o&&(l(a),t.d())}}}function tc(p){let t,a,o,s=p[18](p[10])+"",m,n,c,x,J,j,v,k,V,T,O,W,z,S,ee,te;c=new sl({});let P=p[7]&&_d(p),E=!p[8]&&Md(p),B=p[13]&&Td(p),X=!!p[11]&&kd(p),R=p[2]&&Cd(p),L=!!p[4]&&Fd(p),Q=!!p[6]&&Od(p);return{c(){t=g("div"),a=g("span"),o=new ht(!1),m=r(),n=g("a"),_(c.$$.fragment),J=r(),P&&P.c(),j=r(),E&&E.c(),v=r(),k=g("div"),B&&B.c(),V=r(),X&&X.c(),T=r(),R&&R.c(),O=r(),L&&L.c(),W=r(),Q&&Q.c(),this.h()},l(N){t=f(N,"DIV",{});var U=Z(t);a=f(U,"SPAN",{class:!0,id:!0});var H=Z(a);o=vt(H,!1),m=d(H),n=f(H,"A",{id:!0,class:!0,href:!0});var A=Z(n);M(c.$$.fragment,A),A.forEach(l),J=d(H),P&&P.l(H),H.forEach(l),j=d(U),E&&E.l(U),v=d(U),k=f(U,"DIV",{class:!0});var K=Z(k);B&&B.l(K),V=d(K),X&&X.l(K),T=d(K),R&&R.l(K),O=d(K),L&&L.l(K),W=d(K),Q&&Q.l(K),K.forEach(l),U.forEach(l),this.h()},h(){o.a=m,C(n,"id",p[9]),C(n,"class","header-link invisible with-hover:group-hover:visible pr-2"),C(n,"href",x="#"+p[9]),C(a,"class","group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5"),C(a,"id",p[9]),C(k,"class",z="!mb-10 relative docstring-details "+(p[13]?"max-h-96 overflow-hidden":""))},m(N,U){h(N,t,U),i(t,a),o.m(s,a),i(a,m),i(a,n),w(c,n,null),i(a,J),P&&P.m(a,null),i(t,j),E&&E.m(t,null),i(t,v),i(t,k),B&&B.m(k,null),i(k,V),X&&X.m(k,null),i(k,T),R&&R.m(k,null),i(k,O),L&&L.m(k,null),i(k,W),Q&&Q.m(k,null),p[24](k),S=!0,ee\|\|(te=Ys(ec,"hashchange",p[19]),ee=!0)},p(N,U){(!S\|\|U[0]&1024)&&s!==(s=N[18](N[10])+"")&&o.p(s),(!S\|\|U[0]&512)&&C(n,"id",N[9]),(!S\|\|U[0]&512&&x!==(x="#"+N[9]))&&C(n,"href",x),N[7]?P?P.p(N,U):(P=_d(N),P.c(),P.m(a,null)):P&&(P.d(1),P=null),(!S\|\|U[0]&512)&&C(a,"id",N[9]),N[8]?E&&(E.d(1),E=null):E?E.p(N,U):(E=Md(N),E.c(),E.m(t,v)),N[13]?B?B.p(N,U):(B=Td(N),B.c(),B.m(k,V)):B&&(B.d(1),B=null),N[11]?X?(X.p(N,U),U[0]&2048&&b(X,1)):(X=kd(N),X.c(),b(X,1),X.m(k,T)):X&&(Hs(),y(X,1,1,()=>{X=null}),Qs()),N[2]?R?(R.p(N,U),U[0]&4&&b(R,1)):(R=Cd(N),R.c(),b(R,1),R.m(k,O)):R&&(Hs(),y(R,1,1,()=>{R=null}),Qs()),N[4]?L?L.p(N,U):(L=Fd(N),L.c(),L.m(k,W)):L&&(L.d(1),L=null),N[6]?Q?Q.p(N,U):(Q=Od(N),Q.c(),Q.m(k,null)):Q&&(Q.d(1),Q=null),(!S\|\|U[0]&8192&&z!==(z="!mb-10 relative docstring-details "+(N[13]?"max-h-96 overflow-hidden":"")))&&C(k,"class",z)},i(N){S\|\|(b(c.$$.fragment,N),b(X),b(R),S=!0)},o(N){y(c.$$.fragment,N),y(X),y(R),S=!1},d(N){N&&l(t),$(c),P&&P.d(),E&&E.d(),B&&B.d(),X&&X.d(),R&&R.d(),L&&L.d(),Q&&Q.d(),p[24](null),ee=!1,te()}}}const sn="bg-yellow-50 dark:bg-[#494a3d]";function Ud(p){const t=/\s<p>(((?!<p>).))<\/p>\s*/gms;return p.replace(t,(a,o)=>`<span>${o}</span>`)}function nc(p,t,a){let{anchor:o}=t,{name:s}=t,{parameters:m=[]}=t,{parametersDescription:n}=t,{parameterGroups:c}=t,{returnDescription:x}=t,{returnType:J}=t,{isYield:j=!1}=t,{raiseDescription:v}=t,{raiseType:k}=t,{source:V=void 0}=t,{hashlink:T}=t,{isGetSetDescriptor:O=!1}=t,W,z,S=!1;const ee=(n==null?void 0:n.reduce((U,H)=>{const{name:A,description:K}=H;return{...U,[A]:K}},{}))\|\|{},te=j?"Yields":"Returns",P=te.toLowerCase();lr(()=>{const{hash:U}=window.location;a(0,T=U.substring(1));const K=[...W.querySelectorAll('[href^="#"]')].map(Oo=>Oo.id).includes(T);a(13,S=!K&&W.clientHeight>500),X()});async function E(U,H){H&&(a(13,S=!1),await Rd(),window.location.hash=U)}function B(U){if(U.startsWith("class ")){const H=U.substring(6).split("."),A=H.pop();return`<h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">class</span> <span class="font-medium">${H.join(".")}.</span><span class="font-semibold">${A}</span></span></h3>`}else return O?`<div class="flex items-center rounded-xl py-0.5 break-all bg-gradient-to-r from-green-50/60 to-white dark:from-gray-900 dark:to-gray-950 text-green-700 dark:text-green-300 font-medium px-2"><svg class="fill-current text-2xl text-green-500 inline-block" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><circle cx="12.5" cy="12.5" r="7.5" fill-opacity="0.2"></circle><path d="M12.8454 17.4994C12.077 17.4994 11.3929 17.3946 10.7931 17.185C10.1933 16.9779 9.68621 16.6731 9.27188 16.2709C8.85756 15.871 8.542 15.382 8.3252 14.8039C8.1084 14.2257 8 13.5681 8 12.831C8 12.1035 8.1084 11.4435 8.3252 10.8509C8.54441 10.2583 8.86358 9.75005 9.28272 9.32608C9.70187 8.89971 10.2138 8.57211 10.8184 8.34326C11.4254 8.11442 12.1168 8 12.8924 8C13.6103 8 14.251 8.10479 14.8147 8.31436C15.3808 8.52393 15.8602 8.82263 16.2528 9.21046C16.6479 9.59588 16.9478 10.0548 17.1525 10.5871C17.3597 11.1171 17.4621 11.7036 17.4596 12.3468C17.4621 12.79 17.4235 13.1971 17.344 13.5681C17.2645 13.9391 17.1393 14.2631 16.9682 14.5401C16.7996 14.8147 16.578 15.0327 16.3034 15.1941C16.0288 15.3531 15.6963 15.4434 15.3061 15.4651C15.0267 15.4868 14.8002 15.4663 14.6268 15.4037C14.4534 15.341 14.3209 15.2483 14.2293 15.1254C14.1402 15.0002 14.0824 14.8544 14.0559 14.6882H14.0125C13.9547 14.8328 13.8415 14.9641 13.6729 15.0821C13.5043 15.1977 13.2983 15.288 13.055 15.3531C12.8141 15.4157 12.5576 15.4386 12.2854 15.4217C12.0011 15.4049 11.7313 15.3386 11.476 15.223C11.2231 15.1074 10.9978 14.94 10.8003 14.7208C10.6052 14.5015 10.451 14.2305 10.3378 13.9078C10.227 13.585 10.1704 13.2116 10.168 12.7876C10.1704 12.3685 10.2294 12.0035 10.345 11.6928C10.4631 11.3821 10.6184 11.1207 10.8112 10.9087C11.0063 10.6967 11.2231 10.5305 11.4616 10.4101C11.7 10.2896 11.9397 10.2125 12.1806 10.1788C12.4528 10.1379 12.7106 10.1379 12.9538 10.1788C13.1971 10.2198 13.4019 10.286 13.5681 10.3776C13.7367 10.4691 13.8415 10.5679 13.8825 10.6738H13.9331V10.2692H15.064V13.7957C15.0664 13.962 15.1038 14.0908 15.176 14.1824C15.2483 14.2739 15.3459 14.3197 15.4687 14.3197C15.6349 14.3197 15.7734 14.2462 15.8842 14.0993C15.9975 13.9523 16.0818 13.7271 16.1372 13.4236C16.195 13.1201 16.2239 12.7334 16.2239 12.2637C16.2239 11.8108 16.1637 11.4134 16.0432 11.0713C15.9252 10.7268 15.759 10.4342 15.5446 10.1933C15.3326 9.94998 15.0857 9.75246 14.8039 9.6007C14.522 9.44894 14.2161 9.33813 13.8861 9.26827C13.5585 9.19841 13.2212 9.16349 12.8744 9.16349C12.2745 9.16349 11.7506 9.25502 11.3026 9.4381C10.8545 9.61876 10.4811 9.8729 10.1824 10.2005C9.88374 10.5281 9.65971 10.9123 9.51036 11.3532C9.36342 11.7916 9.28875 12.2697 9.28634 12.7876C9.28875 13.3585 9.36824 13.8644 9.52482 14.3052C9.6838 14.7436 9.91746 15.1122 10.2258 15.4109C10.5341 15.7096 10.9147 15.936 11.3676 16.0902C11.8205 16.2444 12.3408 16.3215 12.9286 16.3215C13.2056 16.3215 13.4766 16.301 13.7415 16.26C14.0065 16.2215 14.2462 16.1733 14.4606 16.1155C14.675 16.0601 14.8472 16.0059 14.9773 15.9529L15.335 17.0008C15.1833 17.0875 14.9773 17.1682 14.7171 17.2428C14.4594 17.3199 14.1679 17.3814 13.8427 17.4271C13.5199 17.4753 13.1875 17.4994 12.8454 17.4994ZM12.6792 14.233C12.9731 14.233 13.2068 14.1764 13.3802 14.0631C13.5561 13.9499 13.6813 13.7825 13.756 13.5609C13.8331 13.3369 13.8692 13.061 13.8644 12.7334C13.862 12.4444 13.8247 12.1999 13.7524 11.9999C13.6825 11.7976 13.5609 11.6446 13.3874 11.541C13.2164 11.4351 12.9779 11.3821 12.672 11.3821C12.4046 11.3821 12.177 11.4387 11.9891 11.5519C11.8036 11.6651 11.6615 11.8241 11.5627 12.0288C11.4664 12.2312 11.417 12.4697 11.4146 12.7443C11.417 12.9996 11.4579 13.2417 11.5374 13.4706C11.6169 13.697 11.7482 13.8813 11.9313 14.0234C12.1144 14.1631 12.3637 14.233 12.6792 14.233Z"></path></svg><span class="text-sm text-green-500 mr-1">property</span><span> ${U}</span></div>`:`<h4 class="!m-0"><span class="flex-1 rounded-xl py-0.5 break-all bg-gradient-to-r from-blue-50/60 to-white dark:from-gray-900 dark:to-gray-950 text-blue-700 dark:text-blue-300 font-medium px-2"><svg width="1em" height="1em" viewBox="0 0 32 33" class="mr-1 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg"><path d="M5.80566 18.3545C4.90766 17.4565 4.90766 16.0005 5.80566 15.1025L14.3768 6.53142C15.2748 5.63342 16.7307 5.63342 17.6287 6.53142L26.1999 15.1025C27.0979 16.0005 27.0979 17.4565 26.1999 18.3545L17.6287 26.9256C16.7307 27.8236 15.2748 27.8236 14.3768 26.9256L5.80566 18.3545Z" fill="currentColor" fill-opacity="0.25"/><path fill-rule="evenodd" clip-rule="evenodd" d="M16.4801 13.9619C16.4801 12.9761 16.7467 12.5436 16.9443 12.3296C17.1764 12.078 17.5731 11.8517 18.2275 11.707C18.8821 11.5623 19.638 11.5342 20.4038 11.5582C20.7804 11.57 21.1341 11.5932 21.4719 11.6156L21.5263 11.6193C21.8195 11.6389 22.1626 11.6618 22.4429 11.6618V7.40825C22.3209 7.40825 22.1219 7.39596 21.7544 7.37149C21.4202 7.34925 20.9976 7.32115 20.5371 7.30672C19.6286 7.27824 18.4672 7.29779 17.3093 7.55377C16.1512 7.8098 14.8404 8.33724 13.8181 9.4452C12.7612 10.5907 12.2266 12.1236 12.2266 13.9619V15.0127H10.6836V19.2662H12.2266V26.6332H16.4801V19.2662H20.3394V15.0127H16.4801V13.9619Z" fill="currentColor"/></svg>${U}</span></h4>`}function X(){var H;const{hash:U}=window.location;if(a(0,T=U.substring(1)),z&&z.classList.remove(...sn.split(" ")),T===o){const A=(H=document.getElementById(T))==null?void 0:H.closest(".docstring");A&&(z=A,z.classList.add(...sn.split(" ")))}}const R=U=>E(`${o}.${U}`,!!ee[U]),L=()=>E(`${o}.${P}`,!!x),Q=()=>a(13,S=!1);function N(U){Gd[U?"unshift":"push"](()=>{W=U,a(12,W)})}return p.$$set=U=>{"anchor"in U&&a(9,o=U.anchor),"name"in U&&a(10,s=U.name),"parameters"in U&&a(1,m=U.parameters),"parametersDescription"in U&&a(11,n=U.parametersDescription),"parameterGroups"in U&&a(2,c=U.parameterGroups),"returnDescription"in U&&a(3,x=U.returnDescription),"returnType"in U&&a(4,J=U.returnType),"isYield"in U&&a(20,j=U.isYield),"raiseDescription"in U&&a(5,v=U.raiseDescription),"raiseType"in U&&a(6,k=U.raiseType),"source"in U&&a(7,V=U.source),"hashlink"in U&&a(0,T=U.hashlink),"isGetSetDescriptor"in U&&a(8,O=U.isGetSetDescriptor)},[T,m,c,x,J,v,k,V,O,o,s,n,W,S,ee,te,P,E,B,X,j,R,L,Q,N]}class I extends tl{constructor(t){super(),nl(this,t,nc,tc,el,{anchor:9,name:10,parameters:1,parametersDescription:11,parameterGroups:2,returnDescription:3,returnType:4,isYield:20,raiseDescription:5,raiseType:6,source:7,hashlink:0,isGetSetDescriptor:8},null,[-1,-1])}}const{window:oc}=Sd;function sc(p){let t,a,o,s,m,n,c,x,J;s=new sl({props:{classNames:"text-smd"}});const j=p[4].default,v=Ld(j,p,p[3],null);return{c(){t=g("div"),a=g("a"),o=g("span"),_(s.$$.fragment),n=r(),v&&v.c(),this.h()},l(k){t=f(k,"DIV",{class:!0});var V=Z(t);a=f(V,"A",{id:!0,class:!0,href:!0});var T=Z(a);o=f(T,"SPAN",{});var O=Z(o);M(s.$$.fragment,O),O.forEach(l),T.forEach(l),n=d(V),v&&v.l(V),V.forEach(l),this.h()},h(){C(a,"id",p[0]),C(a,"class","header-link block pr-0.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),C(a,"href",m=`#${p[0]}`),C(t,"class","relative group rounded-md")},m(k,V){h(k,t,V),i(t,a),i(a,o),w(s,o,null),i(t,n),v&&v.m(t,null),p[5](t),c=!0,x\|\|(J=Ys(oc,"hashchange",p[2]),x=!0)},p(k,[V]){(!c\|\|V&1)&&C(a,"id",k[0]),(!c\|\|V&1&&m!==(m=`#${k[0]}`))&&C(a,"href",m),v&&v.p&&(!c\|\|V&8)&&Ed(v,j,k,k[3],c?Hd(j,k[3],V,null):Pd(k[3]),null)},i(k){c\|\|(b(s.$$.fragment,k),b(v,k),c=!0)},o(k){y(s.$$.fragment,k),y(v,k),c=!1},d(k){k&&l(t),$(s),v&&v.d(k),p[5](null),x=!1,J()}}}const Id="bg-yellow-50 dark:bg-[#494a3d]";function ac(p,t,a){let{$$slots:o={},$$scope:s}=t,{anchor:m}=t,n;function c(){const{hash:J}=window.location,j=J.substring(1);n&&n.classList.remove(...Id.split(" ")),j===m&&n.classList.add(...Id.split(" "))}lr(()=>{c()});function x(J){Gd[J?"unshift":"push"](()=>{n=J,a(1,n)})}return p.$$set=J=>{"anchor"in J&&a(0,m=J.anchor),"$$scope"in J&&a(3,s=J.$$scope)},[m,n,c,s,o,x]}class Y extends tl{constructor(t){super(),nl(this,t,ac,sc,el,{anchor:0})}}function lc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function ic(p){let t,a="Example of masked language modeling using <code>transformers.pipelines</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForMaskedLM

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"roberta-base"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForMaskedLM.from_pretrained(<span class="hljs-string">"roberta-base"</span>, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>mask_token = tokenizer.mask_token
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"fill-mask"</span>, model=model, tokenizer=tokenizer)
	<span class="hljs-meta">>>> </span>outputs = pipe(<span class="hljs-string">"The goal of life is"</span> + mask_token)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1lv30sh"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function rc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function dc(p){let t,a="Example of text generation:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForSeq2SeqLM

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"echarlaix/t5-small-openvino"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForSeq2SeqLM.from_pretrained(<span class="hljs-string">"echarlaix/t5-small-openvino"</span>)
	<span class="hljs-meta">>>> </span>text = <span class="hljs-string">"He never went out without a book under his arm, and he often came back with two."</span>
	<span class="hljs-meta">>>> </span>inputs = tokenizer(text, return_tensors=<span class="hljs-string">"pt"</span>)
	<span class="hljs-meta">>>> </span>gen_tokens = model.generate(**inputs)
	<span class="hljs-meta">>>> </span>outputs = tokenizer.batch_decode(gen_tokens)`,wrap:!1}}),{c(){t=g("p"),t.textContent=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1bvu0cy"&&(t.textContent=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function cc(p){let t,a="Example using <code>transformers.pipeline</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForSeq2SeqLM

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"echarlaix/t5-small-openvino"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForSeq2SeqLM.from_pretrained(<span class="hljs-string">"echarlaix/t5-small-openvino"</span>)
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"translation_en_to_fr"</span>, model=model, tokenizer=tokenizer)
	<span class="hljs-meta">>>> </span>text = <span class="hljs-string">"He never went out without a book under his arm, and he often came back with two."</span>
	<span class="hljs-meta">>>> </span>outputs = pipe(text)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1u1xsxh"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function pc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function mc(p){let t,a="Example of question answering using <code>transformers.pipeline</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForQuestionAnswering

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"distilbert-base-cased-distilled-squad"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForQuestionAnswering.from_pretrained(<span class="hljs-string">"distilbert-base-cased-distilled-squad"</span>, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"question-answering"</span>, model=model, tokenizer=tokenizer)
	<span class="hljs-meta">>>> </span>question, text = <span class="hljs-string">"Who was Jim Henson?"</span>, <span class="hljs-string">"Jim Henson was a nice puppet"</span>
	<span class="hljs-meta">>>> </span>outputs = pipe(question, text)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1m7gyu4"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function uc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function gc(p){let t,a="Example of sequence classification using <code>transformers.pipeline</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForSequenceClassification

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"distilbert-base-uncased-finetuned-sst-2-english"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForSequenceClassification.from_pretrained(<span class="hljs-string">"distilbert-base-uncased-finetuned-sst-2-english"</span>, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"text-classification"</span>, model=model, tokenizer=tokenizer)
	<span class="hljs-meta">>>> </span>outputs = pipe(<span class="hljs-string">"Hello, my dog is cute"</span>)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-o0vbix"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function fc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function hc(p){let t,a="Example of token classification using <code>transformers.pipelines</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForTokenClassification

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"dslim/bert-base-NER"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForTokenClassification.from_pretrained(<span class="hljs-string">"dslim/bert-base-NER"</span>, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"token-classification"</span>, model=model, tokenizer=tokenizer)
	<span class="hljs-meta">>>> </span>outputs = pipe(<span class="hljs-string">"My Name is Peter and I live in New York."</span>)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-6ve2pe"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function vc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function bc(p){let t,a="Example of audio classification using <code>transformers.pipelines</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoFeatureExtractor, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForAudioClassification

	<span class="hljs-meta">>>> </span>preprocessor = AutoFeatureExtractor.from_pretrained(<span class="hljs-string">"superb/hubert-base-superb-er"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForAudioClassification.from_pretrained(<span class="hljs-string">"superb/hubert-base-superb-er"</span>, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"audio-classification"</span>, model=model, feature_extractor=preprocessor)
	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"superb"</span>, <span class="hljs-string">"ks"</span>, split=<span class="hljs-string">"test"</span>)
	<span class="hljs-meta">>>> </span>audio_file = dataset[<span class="hljs-number">3</span>][<span class="hljs-string">"audio"</span>][<span class="hljs-string">"array"</span>]
	<span class="hljs-meta">>>> </span>outputs = pipe(audio_file)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1sgckdf"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function yc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function _c(p){let t,a="Example of audio frame classification:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoFeatureExtractor
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForAudioFrameClassification
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch

	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"hf-internal-testing/librispeech_asr_demo"</span>, <span class="hljs-string">"clean"</span>, split=<span class="hljs-string">"validation"</span>)
	<span class="hljs-meta">>>> </span>dataset = dataset.sort(<span class="hljs-string">"id"</span>)
	<span class="hljs-meta">>>> </span>sampling_rate = dataset.features[<span class="hljs-string">"audio"</span>].sampling_rate

	<span class="hljs-meta">>>> </span>feature_extractor = AutoFeatureExtractor.from_pretrained(<span class="hljs-string">"anton-l/wav2vec2-base-superb-sd"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForAudioFrameClassification.from_pretrained(<span class="hljs-string">"anton-l/wav2vec2-base-superb-sd"</span>, export=<span class="hljs-literal">True</span>)

	<span class="hljs-meta">>>> </span>inputs = feature_extractor(dataset[<span class="hljs-number">0</span>][<span class="hljs-string">"audio"</span>][<span class="hljs-string">"array"</span>], return_tensors=<span class="hljs-string">"pt"</span>, sampling_rate=sampling_rate)
	<span class="hljs-meta">>>> </span> logits = model(**inputs).logits

	<span class="hljs-meta">>>> </span>probabilities = torch.sigmoid(torch.as_tensor(logits)[<span class="hljs-number">0</span>])
	<span class="hljs-meta">>>> </span>labels = (probabilities > <span class="hljs-number">0.5</span>).long()
	<span class="hljs-meta">>>> </span>labels[<span class="hljs-number">0</span>].tolist()`,wrap:!1}}),{c(){t=g("p"),t.textContent=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-12boqdm"&&(t.textContent=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function Mc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function wc(p){let t,a="Example of CTC:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoFeatureExtractor
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForCTC
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset

	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"hf-internal-testing/librispeech_asr_demo"</span>, <span class="hljs-string">"clean"</span>, split=<span class="hljs-string">"validation"</span>)
	<span class="hljs-meta">>>> </span>dataset = dataset.sort(<span class="hljs-string">"id"</span>)
	<span class="hljs-meta">>>> </span>sampling_rate = dataset.features[<span class="hljs-string">"audio"</span>].sampling_rate

	<span class="hljs-meta">>>> </span>processor = AutoFeatureExtractor.from_pretrained(<span class="hljs-string">"facebook/hubert-large-ls960-ft"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForCTC.from_pretrained(<span class="hljs-string">"facebook/hubert-large-ls960-ft"</span>, export=<span class="hljs-literal">True</span>)

	<span class="hljs-meta">>>> </span><span class="hljs-comment"># audio file is decoded on the fly</span>
	<span class="hljs-meta">>>> </span>inputs = processor(dataset[<span class="hljs-number">0</span>][<span class="hljs-string">"audio"</span>][<span class="hljs-string">"array"</span>], sampling_rate=sampling_rate, return_tensors=<span class="hljs-string">"np"</span>)
	<span class="hljs-meta">>>> </span>logits = model(**inputs).logits
	<span class="hljs-meta">>>> </span>predicted_ids = np.argmax(logits, axis=-<span class="hljs-number">1</span>)

	<span class="hljs-meta">>>> </span>transcription = processor.batch_decode(predicted_ids)`,wrap:!1}}),{c(){t=g("p"),t.textContent=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-mdyxnj"&&(t.textContent=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function $c(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function Tc(p){let t,a="Example of Audio XVector:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoFeatureExtractor
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForAudioXVector
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch

	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"hf-internal-testing/librispeech_asr_demo"</span>, <span class="hljs-string">"clean"</span>, split=<span class="hljs-string">"validation"</span>)
	<span class="hljs-meta">>>> </span>dataset = dataset.sort(<span class="hljs-string">"id"</span>)
	<span class="hljs-meta">>>> </span>sampling_rate = dataset.features[<span class="hljs-string">"audio"</span>].sampling_rate

	<span class="hljs-meta">>>> </span>feature_extractor = AutoFeatureExtractor.from_pretrained(<span class="hljs-string">"anton-l/wav2vec2-base-superb-sv"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForAudioXVector.from_pretrained(<span class="hljs-string">"anton-l/wav2vec2-base-superb-sv"</span>, export=<span class="hljs-literal">True</span>)

	<span class="hljs-meta">>>> </span><span class="hljs-comment"># audio file is decoded on the fly</span>
	<span class="hljs-meta">>>> </span>inputs = feature_extractor(
	<span class="hljs-meta">... </span> [d[<span class="hljs-string">"array"</span>] <span class="hljs-keyword">for</span> d <span class="hljs-keyword">in</span> dataset[:<span class="hljs-number">2</span>][<span class="hljs-string">"audio"</span>]], sampling_rate=sampling_rate, return_tensors=<span class="hljs-string">"pt"</span>, padding=<span class="hljs-literal">True</span>
	<span class="hljs-meta">... </span>)
	<span class="hljs-meta">>>> </span> embeddings = model(**inputs).embeddings

	<span class="hljs-meta">>>> </span>embeddings = torch.nn.functional.normalize(embeddings, dim=-<span class="hljs-number">1</span>).cpu()

	<span class="hljs-meta">>>> </span>cosine_sim = torch.nn.CosineSimilarity(dim=-<span class="hljs-number">1</span>)
	<span class="hljs-meta">>>> </span>similarity = cosine_sim(embeddings[<span class="hljs-number">0</span>], embeddings[<span class="hljs-number">1</span>])
	<span class="hljs-meta">>>> </span>threshold = <span class="hljs-number">0.7</span>
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">if</span> similarity < threshold:
	<span class="hljs-meta">... </span> <span class="hljs-built_in">print</span>(<span class="hljs-string">"Speakers are not the same!"</span>)
	<span class="hljs-meta">>>> </span><span class="hljs-built_in">round</span>(similarity.item(), <span class="hljs-number">2</span>)`,wrap:!1}}),{c(){t=g("p"),t.textContent=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1kzdm5c"&&(t.textContent=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function kc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function Vc(p){let t,a="Example of text generation:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForSpeechSeq2Seq
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset

	<span class="hljs-meta">>>> </span>processor = AutoProcessor.from_pretrained(<span class="hljs-string">"openai/whisper-tiny"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForSpeechSeq2Seq.from_pretrained(<span class="hljs-string">"openai/whisper-tiny"</span>)

	<span class="hljs-meta">>>> </span>ds = load_dataset(<span class="hljs-string">"hf-internal-testing/librispeech_asr_dummy"</span>, <span class="hljs-string">"clean"</span>, split=<span class="hljs-string">"validation"</span>)
	<span class="hljs-meta">>>> </span>inputs = processor.feature_extractor(ds[<span class="hljs-number">0</span>][<span class="hljs-string">"audio"</span>][<span class="hljs-string">"array"</span>], return_tensors=<span class="hljs-string">"pt"</span>)

	<span class="hljs-meta">>>> </span>gen_tokens = model.generate(inputs=inputs.input_features)
	<span class="hljs-meta">>>> </span>outputs = processor.tokenizer.batch_decode(gen_tokens)`,wrap:!1}}),{c(){t=g("p"),t.textContent=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1bvu0cy"&&(t.textContent=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function Cc(p){let t,a="Example using <code>transformers.pipeline</code>:",o,s,m;return s=new D({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMEF1dG9Qcm9jZXNzb3IlMkMlMjBwaXBlbGluZSUwQWZyb20lMjBvcHRpbXVtLmludGVsJTIwaW1wb3J0JTIwT1ZNb2RlbEZvclNwZWVjaFNlcTJTZXElMEFmcm9tJTIwZGF0YXNldHMlMjBpbXBvcnQlMjBsb2FkX2RhdGFzZXQlMEElMEFwcm9jZXNzb3IlMjAlM0QlMjBBdXRvUHJvY2Vzc29yLmZyb21fcHJldHJhaW5lZCglMjJvcGVuYWklMkZ3aGlzcGVyLXRpbnklMjIpJTBBbW9kZWwlMjAlM0QlMjBPVk1vZGVsRm9yU3BlZWNoU2VxMlNlcS5mcm9tX3ByZXRyYWluZWQoJTIyb3BlbmFpJTJGd2hpc3Blci10aW55JTIyKSUwQXNwZWVjaF9yZWNvZ25pdGlvbiUyMCUzRCUyMHBpcGVsaW5lKCUyMmF1dG9tYXRpYy1zcGVlY2gtcmVjb2duaXRpb24lMjIlMkMlMjBtb2RlbCUzRG1vZGVsJTJDJTIwdG9rZW5pemVyJTNEcHJvY2Vzc29yLnRva2VuaXplciUyQyUyMGZlYXR1cmVfZXh0cmFjdG9yJTNEcHJvY2Vzc29yLmZlYXR1cmVfZXh0cmFjdG9yKSUwQSUwQWRzJTIwJTNEJTIwbG9hZF9kYXRhc2V0KCUyMmhmLWludGVybmFsLXRlc3RpbmclMkZsaWJyaXNwZWVjaF9hc3JfZHVtbXklMjIlMkMlMjAlMjJjbGVhbiUyMiUyQyUyMHNwbGl0JTNEJTIydmFsaWRhdGlvbiUyMiklMEFwcmVkJTIwJTNEJTIwc3BlZWNoX3JlY29nbml0aW9uKGRzJTVCMCU1RCU1QiUyMmF1ZGlvJTIyJTVEJTVCJTIyYXJyYXklMjIlNUQp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForSpeechSeq2Seq
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset

	<span class="hljs-meta">>>> </span>processor = AutoProcessor.from_pretrained(<span class="hljs-string">"openai/whisper-tiny"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForSpeechSeq2Seq.from_pretrained(<span class="hljs-string">"openai/whisper-tiny"</span>)
	<span class="hljs-meta">>>> </span>speech_recognition = pipeline(<span class="hljs-string">"automatic-speech-recognition"</span>, model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor)

	<span class="hljs-meta">>>> </span>ds = load_dataset(<span class="hljs-string">"hf-internal-testing/librispeech_asr_dummy"</span>, <span class="hljs-string">"clean"</span>, split=<span class="hljs-string">"validation"</span>)
	<span class="hljs-meta">>>> </span>pred = speech_recognition(ds[<span class="hljs-number">0</span>][<span class="hljs-string">"audio"</span>][<span class="hljs-string">"array"</span>])`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1u1xsxh"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function Jc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function jc(p){let t,a="Example of image classification using <code>transformers.pipelines</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoFeatureExtractor, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForImageClassification

	<span class="hljs-meta">>>> </span>preprocessor = AutoFeatureExtractor.from_pretrained(<span class="hljs-string">"google/vit-base-patch16-224"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForImageClassification.from_pretrained(<span class="hljs-string">"google/vit-base-patch16-224"</span>, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>model.reshape(batch_size=<span class="hljs-number">1</span>, sequence_length=<span class="hljs-number">3</span>, height=<span class="hljs-number">224</span>, width=<span class="hljs-number">224</span>)
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"image-classification"</span>, model=model, feature_extractor=preprocessor)
	<span class="hljs-meta">>>> </span>url = <span class="hljs-string">"http://images.cocodataset.org/val2017/000000039769.jpg"</span>
	<span class="hljs-meta">>>> </span>outputs = pipe(url)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1w9p9ki"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function Fc(p){let t,a='models hosted on <a href="https://huggingface.co/timm" rel="nofollow">HuggingFaceHub</a>. Example:',o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel.openvino.modeling_timm <span class="hljs-keyword">import</span> TimmImageProcessor
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForImageClassification

	<span class="hljs-meta">>>> </span>model_id = <span class="hljs-string">"timm/vit_tiny_patch16_224.augreg_in21k"</span>
	<span class="hljs-meta">>>> </span>preprocessor = TimmImageProcessor.from_pretrained(model_id)
	<span class="hljs-meta">>>> </span>model = OVModelForImageClassification.from_pretrained(model_id, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"image-classification"</span>, model=model, feature_extractor=preprocessor)
	<span class="hljs-meta">>>> </span>url = <span class="hljs-string">"http://images.cocodataset.org/val2017/000000039769.jpg"</span>
	<span class="hljs-meta">>>> </span>outputs = pipe(url)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1b3qe4z"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function xc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function Oc(p){let t,a="Example of text generation:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor, AutoTokenizer
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForVision2Seq
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> requests


	<span class="hljs-meta">>>> </span>processor = AutoProcessor.from_pretrained(<span class="hljs-string">"microsoft/trocr-small-handwritten"</span>)
	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"microsoft/trocr-small-handwritten"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForVision2Seq.from_pretrained(<span class="hljs-string">"microsoft/trocr-small-handwritten"</span>, export=<span class="hljs-literal">True</span>)

	<span class="hljs-meta">>>> </span>url = <span class="hljs-string">"https://fki.tic.heia-fr.ch/static/img/a01-122-02-00.jpg"</span>
	<span class="hljs-meta">>>> </span>image = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw)
	<span class="hljs-meta">>>> </span>inputs = processor(image, return_tensors=<span class="hljs-string">"pt"</span>)

	<span class="hljs-meta">>>> </span>gen_tokens = model.generate(**inputs)
	<span class="hljs-meta">>>> </span>outputs = tokenizer.batch_decode(gen_tokens, skip_special_tokens=<span class="hljs-literal">True</span>)
	`,wrap:!1}}),{c(){t=g("p"),t.textContent=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1bvu0cy"&&(t.textContent=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function Zc(p){let t,a="Example using <code>transformers.pipeline</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor, AutoTokenizer, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForVision2Seq
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> requests


	<span class="hljs-meta">>>> </span>processor = AutoProcessor.from_pretrained(<span class="hljs-string">"microsoft/trocr-small-handwritten"</span>)
	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"microsoft/trocr-small-handwritten"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForVision2Seq.from_pretrained(<span class="hljs-string">"microsoft/trocr-small-handwritten"</span>, export=<span class="hljs-literal">True</span>)

	<span class="hljs-meta">>>> </span>url = <span class="hljs-string">"https://fki.tic.heia-fr.ch/static/img/a01-122-02-00.jpg"</span>
	<span class="hljs-meta">>>> </span>image = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw)

	<span class="hljs-meta">>>> </span>image_to_text = pipeline(<span class="hljs-string">"image-to-text"</span>, model=model, tokenizer=tokenizer, feature_extractor=processor, image_processor=processor)
	<span class="hljs-meta">>>> </span>pred = image_to_text(image)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1u1xsxh"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function Uc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function Ic(p){let t,a="Example of pix2struct:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForPix2Struct
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> requests

	<span class="hljs-meta">>>> </span>processor = AutoProcessor.from_pretrained(<span class="hljs-string">"google/pix2struct-ai2d-base"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForPix2Struct.from_pretrained(<span class="hljs-string">"google/pix2struct-ai2d-base"</span>, export=<span class="hljs-literal">True</span>)

	<span class="hljs-meta">>>> </span>url = <span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"</span>
	<span class="hljs-meta">>>> </span>image = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw)
	<span class="hljs-meta">>>> </span>question = <span class="hljs-string">"What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud"</span>
	<span class="hljs-meta">>>> </span>inputs = processor(images=image, text=question, return_tensors=<span class="hljs-string">"pt"</span>)

	<span class="hljs-meta">>>> </span>gen_tokens = model.generate(**inputs)
	<span class="hljs-meta">>>> </span>outputs = processor.batch_decode(gen_tokens, skip_special_tokens=<span class="hljs-literal">True</span>)`,wrap:!1}}),{c(){t=g("p"),t.textContent=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-11ikyn3"&&(t.textContent=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function Nc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function Wc(p){let t,a="Example of custom tasks (e.g. a sentence transformers with a pooler head):",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForCustomTasks

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"IlyasMoutawwakil/sbert-all-MiniLM-L6-v2-with-pooler"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForCustomTasks.from_pretrained(<span class="hljs-string">"IlyasMoutawwakil/sbert-all-MiniLM-L6-v2-with-pooler"</span>)

	<span class="hljs-meta">>>> </span>inputs = tokenizer(<span class="hljs-string">"I love burritos!"</span>, return_tensors=<span class="hljs-string">"np"</span>)

	<span class="hljs-meta">>>> </span>outputs = model(**inputs)
	<span class="hljs-meta">>>> </span>last_hidden_state = outputs.last_hidden_state
	<span class="hljs-meta">>>> </span>pooler_output = outputs.pooler_output`,wrap:!1}}),{c(){t=g("p"),t.textContent=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-1xuxpxx"&&(t.textContent=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function qc(p){let t,a=`Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code>
	instance afterwards instead of this since the former takes care of running the pre and post processing steps while
	the latter silently ignores them.`;return{c(){t=g("p"),t.innerHTML=a},l(o){t=f(o,"P",{"data-svelte-h":!0}),F(t)!=="svelte-fincs2"&&(t.innerHTML=a)},m(o,s){h(o,t,s)},p:q,d(o){o&&l(t)}}}function Gc(p){let t,a="Example of feature extraction using <code>transformers.pipelines</code>:",o,s,m;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, pipeline
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVModelForFeatureExtraction

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"sentence-transformers/all-MiniLM-L6-v2"</span>)
	<span class="hljs-meta">>>> </span>model = OVModelForFeatureExtraction.from_pretrained(<span class="hljs-string">"sentence-transformers/all-MiniLM-L6-v2"</span>, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>pipe = pipeline(<span class="hljs-string">"feature-extraction"</span>, model=model, tokenizer=tokenizer)
	<span class="hljs-meta">>>> </span>outputs = pipe(<span class="hljs-string">"My Name is Peter and I live in New York."</span>)`,wrap:!1}}),{c(){t=g("p"),t.innerHTML=a,o=r(),_(s.$$.fragment)},l(n){t=f(n,"P",{"data-svelte-h":!0}),F(t)!=="svelte-9brije"&&(t.innerHTML=a),o=d(n),M(s.$$.fragment,n)},m(n,c){h(n,t,c),h(n,o,c),w(s,n,c),m=!0},p:q,i(n){m\|\|(b(s.$$.fragment,n),m=!0)},o(n){y(s.$$.fragment,n),m=!1},d(n){n&&(l(t),l(o)),$(s,n)}}}function Xc(p){let t,a,o,s,m,n,c,x,J,j,v,k,V,T,O="Base OVModel class.",W,z,S,ee,te,P="Instantiate a pretrained model from a pre-trained model configuration.",E,B,X,R,L,Q="Propagates the given input shapes on the model’s layers, fixing the inputs shapes of the model.",N,U,H,A,K="The following classes are available for the following natural language processing tasks.",Oo,an,Ds,ne,ln,al,Zo,ir=`OpenVINO Model with a causal language modeling head on top (linear layer with weights tied to the input
	embeddings).`,ll,Uo,rr=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,il,Io,rn,rl,No,dn,As,cn,Ks,pe,pn,dl,Wo,dr="OpenVINO Model with a MaskedLMOutput for masked language modeling tasks.",cl,qo,cr=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,pl,Ce,mn,ml,Go,pr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForMaskedLM">OVModelForMaskedLM</a> forward method, overrides the <code>__call__</code> special method.',ul,bt,gl,yt,ea,un,ta,qe,gn,fl,Xo,mr="Sequence-to-sequence model with a language modeling head for OpenVINO inference.",hl,ie,fn,vl,zo,ur='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForSeq2SeqLM">OVModelForSeq2SeqLM</a> forward method, overrides the <code>__call__</code> special method.',bl,_t,yl,Mt,_l,wt,na,hn,oa,me,vn,Ml,So,gr="OpenVINO Model with a QuestionAnsweringModelOutput for extractive question-answering tasks.",wl,Bo,fr=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,$l,Je,bn,Tl,Ro,hr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForQuestionAnswering">OVModelForQuestionAnswering</a> forward method, overrides the <code>__call__</code> special method.',kl,$t,Vl,Tt,sa,yn,aa,ue,_n,Cl,Lo,vr="OpenVINO Model with a SequenceClassifierOutput for sequence classification tasks.",Jl,Eo,br=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,jl,je,Mn,Fl,Po,yr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForSequenceClassification">OVModelForSequenceClassification</a> forward method, overrides the <code>__call__</code> special method.',xl,kt,Ol,Vt,la,wn,ia,ge,$n,Zl,Ho,_r="OpenVINO Model with a TokenClassifierOutput for token classification tasks.",Ul,Qo,Mr=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,Il,Fe,Tn,Nl,Yo,wr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForTokenClassification">OVModelForTokenClassification</a> forward method, overrides the <code>__call__</code> special method.',Wl,Ct,ql,Jt,ra,kn,da,Vn,$r="The following classes are available for the following audio tasks.",ca,Cn,pa,fe,Jn,Gl,Do,Tr="OpenVINO Model with a SequenceClassifierOutput for audio classification tasks.",Xl,Ao,kr=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,zl,xe,jn,Sl,Ko,Vr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForAudioClassification">OVModelForAudioClassification</a> forward method, overrides the <code>__call__</code> special method.',Bl,jt,Rl,Ft,ma,Fn,ua,oe,xn,Ll,es,Cr="OpenVINO Model for with a frame classification head on top for tasks like Speaker Diarization.",El,ts,Jr=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,Pl,ns,jr="Audio Frame Classification model for OpenVINO.",Hl,Oe,On,Ql,os,Fr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForAudioFrameClassification">OVModelForAudioFrameClassification</a> forward method, overrides the <code>__call__</code> special method.',Yl,xt,Dl,Ot,ga,Zn,fa,se,Un,Al,ss,xr="Onnx Model with a language modeling head on top for Connectionist Temporal Classification (CTC).",Kl,as,Or=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,ei,ls,Zr="CTC model for OpenVINO.",ti,Ze,In,ni,is,Ur='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForCTC">OVModelForCTC</a> forward method, overrides the <code>__call__</code> special method.',oi,Zt,si,Ut,ha,Nn,va,ae,Wn,ai,rs,Ir="Onnx Model with an XVector feature extraction head on top for tasks like Speaker Verification.",li,ds,Nr=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,ii,cs,Wr="Audio XVector model for OpenVINO.",ri,Ue,qn,di,ps,qr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForAudioXVector">OVModelForAudioXVector</a> forward method, overrides the <code>__call__</code> special method.',ci,It,pi,Nt,ba,Gn,ya,Ge,Xn,mi,ms,Gr="Speech Sequence-to-sequence model with a language modeling head for OpenVINO inference. This class officially supports whisper, speech_to_text.",ui,re,zn,gi,us,Xr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForSpeechSeq2Seq">OVModelForSpeechSeq2Seq</a> forward method, overrides the <code>__call__</code> special method.',fi,Wt,hi,qt,vi,Gt,_a,Sn,Ma,Bn,zr="The following classes are available for the following computer vision tasks.",wa,Rn,$a,he,Ln,bi,gs,Sr="OpenVINO Model with a ImageClassifierOutput for image classification tasks.",yi,fs,Br=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,_i,de,En,Mi,hs,Rr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForImageClassification">OVModelForImageClassification</a> forward method, overrides the <code>__call__</code> special method.',wi,Xt,$i,zt,Ti,St,Ta,Pn,ka,Hn,Lr="The following classes are available for the following multimodal tasks.",Va,Qn,Ca,Xe,Yn,ki,vs,Er="VisionEncoderDecoder Sequence-to-sequence model with a language modeling head for OpenVINO inference.",Vi,ce,Dn,Ci,bs,Pr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForVision2Seq">OVModelForVision2Seq</a> forward method, overrides the <code>__call__</code> special method.',Ji,Bt,ji,Rt,Fi,Lt,Ja,An,ja,ze,Kn,xi,ys,Hr="Pix2Struct model with a language modeling head for OpenVINO inference.",Oi,Ie,eo,Zi,_s,Qr='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForPix2Struct">OVModelForPix2Struct</a> forward method, overrides the <code>__call__</code> special method.',Ui,Et,Ii,Pt,Fa,to,xa,no,Oa,ve,oo,Ni,Ms,Yr="OpenVINO Model for custom tasks. It can be used to leverage the inference acceleration for any single-file OpenVINO model, that may use custom inputs and outputs.",Wi,ws,Dr=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,qi,Ne,so,Gi,$s,Ar='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForCustomTasks">OVModelForCustomTasks</a> forward method, overrides the <code>__call__</code> special method.',Xi,Ht,zi,Qt,Za,ao,Ua,be,lo,Si,Ts,Kr="OpenVINO Model with a BaseModelOutput for feature extraction tasks.",Bi,ks,ed=`This model inherits from <code>optimum.intel.openvino.modeling.OVBaseModel</code>. Check the superclass documentation for the generic methods the
	library implements for all its model (such as downloading or saving)`,Ri,We,io,Li,Vs,td='The <a href="/docs/optimum.intel/pr_1684/en/openvino/reference#optimum.intel.OVModelForFeatureExtraction">OVModelForFeatureExtraction</a> forward method, overrides the <code>__call__</code> special method.',Ei,Yt,Pi,Dt,Ia,ro,Na,co,Wa,Se,po,Hi,Cs,nd='OpenVINO-powered stable diffusion pipeline corresponding to <a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion#diffusers.StableDiffusionPipeline" rel="nofollow">diffusers.StableDiffusionPipeline</a>.',Qi,Js,mo,qa,uo,Ga,Be,go,Yi,js,od='OpenVINO-powered stable diffusion pipeline corresponding to <a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#diffusers.StableDiffusionXLPipeline" rel="nofollow">diffusers.StableDiffusionXLPipeline</a>.',Di,Fs,fo,Xa,ho,za,Re,vo,Ai,xs,sd='OpenVINO-powered stable diffusion pipeline corresponding to <a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/latent_consistency#diffusers.LatentConsistencyModelPipeline" rel="nofollow">diffusers.LatentConsistencyModelPipeline</a>.',Ki,Os,bo,Sa,yo,Ba,_o,Ra,Le,Mo,er,Zs,ad='OpenVINO-powered stable diffusion pipeline corresponding to <a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_img2img#diffusers.StableDiffusionImg2ImgPipeline" rel="nofollow">diffusers.StableDiffusionImg2ImgPipeline</a>.',tr,Us,wo,La,$o,Ea,Ee,To,nr,Is,ld='OpenVINO-powered stable diffusion pipeline corresponding to <a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#diffusers.StableDiffusionXLImg2ImgPipeline" rel="nofollow">diffusers.StableDiffusionXLImg2ImgPipeline</a>.',or,Ns,ko,Pa,Vo,Ha,Co,Qa,Pe,Jo,sr,Ws,id='OpenVINO-powered stable diffusion pipeline corresponding to <a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_inpaint#diffusers.StableDiffusionInpaintPipeline" rel="nofollow">diffusers.StableDiffusionInpaintPipeline</a>.',ar,qs,jo,Ya,Ls,Da;return m=new Yd({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),c=new G({props:{title:"Models",local:"models",headingTag:"h1"}}),J=new G({props:{title:"Generic model classes",local:"optimum.intel.openvino.modeling_base.OVBaseModel",headingTag:"h2"}}),k=new I({props:{name:"class optimum.intel.openvino.modeling_base.OVBaseModel",anchor:"optimum.intel.openvino.modeling_base.OVBaseModel",parameters:[{name:"model",val:": Model"},{name:"config",val:": PreTrainedConfig = None"},{name:"device",val:": str = 'CPU'"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict, NoneType] = None"},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L189"}}),S=new I({props:{name:"from_pretrained",anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained",parameters:[{name:"model_id",val:": typing.Union[str, pathlib.Path]"},{name:"export",val:": bool = False"},{name:"force_download",val:": bool = False"},{name:"token",val:": typing.Union[bool, str, NoneType] = None"},{name:"cache_dir",val:": str = '/home/runner/.cache/huggingface/hub'"},{name:"subfolder",val:": str = ''"},{name:"config",val:": typing.Optional[transformers.configuration_utils.PreTrainedConfig] = None"},{name:"local_files_only",val:": bool = False"},{name:"trust_remote_code",val:": bool = False"},{name:"revision",val:": typing.Optional[str] = None"},{name:"kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.model_id",description:`<strong>model_id</strong> (<code>Union[str, Path]</code>) —
	Can be either:
	<ul>
	<li>A string, the <em>model id</em> of a pretrained model hosted inside a model repo on huggingface.co.
	Valid model ids can be located at the root-level, like <code>bert-base-uncased</code>, or namespaced under a
	user or organization name, like <code>dbmdz/bert-base-german-cased</code>.</li>
	<li>A path to a <em>directory</em> containing a model saved using <code>~OptimizedModel.save_pretrained</code>,
	e.g., <code>./my_model_directory/</code>.</li>
	</ul>`,name:"model_id"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.export",description:`<strong>export</strong> (<code>bool</code>, defaults to <code>False</code>) —
	Defines whether the provided <code>model_id</code> needs to be exported to the targeted format.`,name:"export"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.force_download",description:`<strong>force_download</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Whether or not to force the (re-)download of the model weights and configuration files, overriding the
	cached versions if they exist.`,name:"force_download"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.token",description:`<strong>token</strong> (<code>Optional[Union[bool,str]]</code>, defaults to <code>None</code>) —
	The token to use as HTTP bearer authorization for remote files. If <code>True</code>, will use the token generated
	when running <code>huggingface-cli login</code> (stored in <code>huggingface_hub.constants.HF_TOKEN_PATH</code>).`,name:"token"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.cache_dir",description:`<strong>cache_dir</strong> (<code>Optional[str]</code>, defaults to <code>None</code>) —
	Path to a directory in which a downloaded pretrained model configuration should be cached if the
	standard cache should not be used.`,name:"cache_dir"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, defaults to <code>""</code>) —
	In case the relevant files are located inside a subfolder of the model repo either locally or on huggingface.co, you can
	specify the folder name here.`,name:"subfolder"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.config",description:`<strong>config</strong> (<code>Optional[transformers.PretrainedConfig]</code>, defaults to <code>None</code>) —
	The model configuration.`,name:"config"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.local_files_only",description:`<strong>local_files_only</strong> (<code>Optional[bool]</code>, defaults to <code>False</code>) —
	Whether or not to only look at local files (i.e., do not try to download the model).`,name:"local_files_only"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.trust_remote_code",description:`<strong>trust_remote_code</strong> (<code>bool</code>, defaults to <code>False</code>) —
	Whether or not to allow for custom code defined on the Hub in their own modeling. This option should only be set
	to <code>True</code> for repositories you trust and in which you have read the code, as it will execute code present on
	the Hub on your local machine.`,name:"trust_remote_code"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.from_pretrained.revision",description:`<strong>revision</strong> (<code>Optional[str]</code>, defaults to <code>None</code>) —
	The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
	git-based system for storing models and other artifacts on huggingface.co, so <code>revision</code> can be any
	identifier allowed by git.`,name:"revision"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L560"}}),X=new I({props:{name:"reshape",anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.reshape",parameters:[{name:"batch_size",val:": int"},{name:"sequence_length",val:": int"},{name:"height",val:": int = None"},{name:"width",val:": int = None"}],parametersDescription:[{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.reshape.batch_size",description:`<strong>batch_size</strong> (<code>int</code>) —
	The batch size.`,name:"batch_size"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.reshape.sequence_length",description:`<strong>sequence_length</strong> (<code>int</code>) —
	The sequence length or number of channels.`,name:"sequence_length"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.reshape.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>) —
	The image height.`,name:"height"},{anchor:"optimum.intel.openvino.modeling_base.OVBaseModel.reshape.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>) —
	The image width.`,name:"width"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L936"}}),U=new G({props:{title:"Natural Language Processing",local:"natural-language-processing",headingTag:"h2"}}),an=new G({props:{title:"OVModelForCausalLM",local:"optimum.intel.OVModelForCausalLM",headingTag:"h3"}}),ln=new I({props:{name:"class optimum.intel.OVModelForCausalLM",anchor:"optimum.intel.OVModelForCausalLM",parameters:[{name:"model",val:": Model"},{name:"config",val:": PreTrainedConfig = None"},{name:"device",val:": str = 'CPU'"},{name:"dynamic_shapes",val:": bool = None"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict, NoneType] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForCausalLM.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForCausalLM.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForCausalLM.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForCausalLM.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForCausalLM.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForCausalLM.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_decoder.py#L453"}}),rn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForCausalLM.forward",parameters:[{name:"input_ids",val:": LongTensor"},{name:"attention_mask",val:": typing.Optional[torch.LongTensor] = None"},{name:"past_key_values",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.FloatTensor]]] = None"},{name:"position_ids",val:": typing.Optional[torch.LongTensor] = None"},{name:"token_type_ids",val:": typing.Optional[torch.LongTensor] = None"},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_decoder.py#L566"}}),dn=new I({props:{name:"generate",anchor:"optimum.intel.OVModelForCausalLM.generate",parameters:[{name:"inputs",val:": typing.Optional[torch.Tensor] = None"},{name:"generation_config",val:": typing.Optional[transformers.generation.configuration_utils.GenerationConfig] = None"},{name:"logits_processor",val:": typing.Optional[transformers.generation.logits_process.LogitsProcessorList] = None"},{name:"stopping_criteria",val:": typing.Optional[transformers.generation.stopping_criteria.StoppingCriteriaList] = None"},{name:"prefix_allowed_tokens_fn",val:": typing.Optional[typing.Callable[[int, torch.Tensor], typing.List[int]]] = None"},{name:"synced_gpus",val:": typing.Optional[bool] = None"},{name:"assistant_model",val:": typing.Optional[ForwardRef('PreTrainedModel')] = None"},{name:"streamer",val:": typing.Optional[ForwardRef('BaseStreamer')] = None"},{name:"negative_prompt_ids",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_attention_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_decoder.py#L747"}}),cn=new G({props:{title:"OVModelForMaskedLM",local:"optimum.intel.OVModelForMaskedLM",headingTag:"h3"}}),pn=new I({props:{name:"class optimum.intel.OVModelForMaskedLM",anchor:"optimum.intel.OVModelForMaskedLM",parameters:[{name:"model",val:" = None"},{name:"config",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForMaskedLM.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForMaskedLM.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForMaskedLM.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForMaskedLM.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForMaskedLM.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForMaskedLM.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L448"}}),mn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForMaskedLM.forward",parameters:[{name:"input_ids",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"attention_mask",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"token_type_ids",val:": typing.Union[torch.Tensor, numpy.ndarray, NoneType] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForMaskedLM.forward.input_ids",description:`<strong>input_ids</strong> (<code>torch.Tensor</code>) —
	Indices of input sequence tokens in the vocabulary.
	Indices can be obtained using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autotokenizer" rel="nofollow"><code>AutoTokenizer</code></a>.
	<a href="https://huggingface.co/docs/transformers/glossary#input-ids" rel="nofollow">What are input IDs?</a>`,name:"input_ids"},{anchor:"optimum.intel.OVModelForMaskedLM.forward.attention_mask",description:`<strong>attention_mask</strong> (<code>torch.Tensor</code>), <em>optional</em>) —
	Mask to avoid performing attention on padding token indices. Mask values selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>not masked</strong>,</li>
	<li>0 for tokens that are <strong>masked</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#attention-mask" rel="nofollow">What are attention masks?</a></li>
	</ul>`,name:"attention_mask"},{anchor:"optimum.intel.OVModelForMaskedLM.forward.token_type_ids",description:`<strong>token_type_ids</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Segment token indices to indicate first and second portions of the inputs. Indices are selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>sentence A</strong>,</li>
	<li>0 for tokens that are <strong>sentence B</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#token-type-ids" rel="nofollow">What are token type IDs?</a></li>
	</ul>`,name:"token_type_ids"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L455"}}),bt=new le({props:{$$slots:{default:[lc]},$$scope:{ctx:p}}}),yt=new Y({props:{anchor:"optimum.intel.OVModelForMaskedLM.forward.example",$$slots:{default:[ic]},$$scope:{ctx:p}}}),un=new G({props:{title:"OVModelForSeq2SeqLM",local:"optimum.intel.OVModelForSeq2SeqLM",headingTag:"h3"}}),gn=new I({props:{name:"class optimum.intel.OVModelForSeq2SeqLM",anchor:"optimum.intel.OVModelForSeq2SeqLM",parameters:[{name:"encoder",val:": Model"},{name:"decoder",val:": Model"},{name:"decoder_with_past",val:": Model = None"},{name:"config",val:": PreTrainedConfig = None"},{name:"device",val:": str = 'CPU'"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForSeq2SeqLM.encoder",description:`<strong>encoder</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the encoder.`,name:"encoder"},{anchor:"optimum.intel.OVModelForSeq2SeqLM.decoder",description:`<strong>decoder</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the decoder.`,name:"decoder"},{anchor:"optimum.intel.OVModelForSeq2SeqLM.decoder_with_past",description:`<strong>decoder_with_past</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the decoder with past key values.`,name:"decoder_with_past"},{anchor:"optimum.intel.OVModelForSeq2SeqLM.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) —
	<a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is an instance of the configuration associated to the model. Initializing with a config file does
	not load the weights associated with the model, only the configuration.`,name:"config"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_seq2seq.py#L329"}}),fn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForSeq2SeqLM.forward",parameters:[{name:"input_ids",val:": LongTensor = None"},{name:"attention_mask",val:": typing.Optional[torch.FloatTensor] = None"},{name:"decoder_input_ids",val:": typing.Optional[torch.LongTensor] = None"},{name:"decoder_attention_mask",val:": typing.Optional[torch.LongTensor] = None"},{name:"encoder_outputs",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None"},{name:"past_key_values",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None"},{name:"cache_position",val:": typing.Optional[torch.LongTensor] = None"},{name:"labels",val:": typing.Optional[torch.LongTensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForSeq2SeqLM.forward.input_ids",description:`<strong>input_ids</strong> (<code>torch.LongTensor</code>) —
	Indices of input sequence tokens in the vocabulary of shape <code>(batch_size, encoder_sequence_length)</code>.`,name:"input_ids"},{anchor:"optimum.intel.OVModelForSeq2SeqLM.forward.attention_mask",description:`<strong>attention_mask</strong> (<code>torch.LongTensor</code>) —
	Mask to avoid performing attention on padding token indices, of shape
	<code>(batch_size, encoder_sequence_length)</code>. Mask values selected in <code>[0, 1]</code>.`,name:"attention_mask"},{anchor:"optimum.intel.OVModelForSeq2SeqLM.forward.decoder_input_ids",description:`<strong>decoder_input_ids</strong> (<code>torch.LongTensor</code>) —
	Indices of decoder input sequence tokens in the vocabulary of shape <code>(batch_size, decoder_sequence_length)</code>.`,name:"decoder_input_ids"},{anchor:"optimum.intel.OVModelForSeq2SeqLM.forward.encoder_outputs",description:`<strong>encoder_outputs</strong> (<code>torch.FloatTensor</code>) —
	The encoder <code>last_hidden_state</code> of shape <code>(batch_size, encoder_sequence_length, hidden_size)</code>.`,name:"encoder_outputs"},{anchor:"optimum.intel.OVModelForSeq2SeqLM.forward.past_key_values",description:`<strong>past_key_values</strong> (<code>tuple(tuple(torch.FloatTensor), optional)</code> —
	Contains the precomputed key and value hidden states of the attention blocks used to speed up decoding.
	The tuple is of length <code>config.n_layers</code> with each tuple having 2 tensors of shape
	<code>(batch_size, num_heads, decoder_sequence_length, embed_size_per_head)</code> and 2 additional tensors of shape
	<code>(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)</code>.`,name:"past_key_values"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_seq2seq.py#L644"}}),_t=new le({props:{$$slots:{default:[rc]},$$scope:{ctx:p}}}),Mt=new Y({props:{anchor:"optimum.intel.OVModelForSeq2SeqLM.forward.example",$$slots:{default:[dc]},$$scope:{ctx:p}}}),wt=new Y({props:{anchor:"optimum.intel.OVModelForSeq2SeqLM.forward.example-2",$$slots:{default:[cc]},$$scope:{ctx:p}}}),hn=new G({props:{title:"OVModelForQuestionAnswering",local:"optimum.intel.OVModelForQuestionAnswering",headingTag:"h3"}}),vn=new I({props:{name:"class optimum.intel.OVModelForQuestionAnswering",anchor:"optimum.intel.OVModelForQuestionAnswering",parameters:[{name:"model",val:" = None"},{name:"config",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForQuestionAnswering.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForQuestionAnswering.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForQuestionAnswering.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForQuestionAnswering.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForQuestionAnswering.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForQuestionAnswering.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L219"}}),bn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForQuestionAnswering.forward",parameters:[{name:"input_ids",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"attention_mask",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"token_type_ids",val:": typing.Union[torch.Tensor, numpy.ndarray, NoneType] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForQuestionAnswering.forward.input_ids",description:`<strong>input_ids</strong> (<code>torch.Tensor</code>) —
	Indices of input sequence tokens in the vocabulary.
	Indices can be obtained using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autotokenizer" rel="nofollow"><code>AutoTokenizer</code></a>.
	<a href="https://huggingface.co/docs/transformers/glossary#input-ids" rel="nofollow">What are input IDs?</a>`,name:"input_ids"},{anchor:"optimum.intel.OVModelForQuestionAnswering.forward.attention_mask",description:`<strong>attention_mask</strong> (<code>torch.Tensor</code>), <em>optional</em>) —
	Mask to avoid performing attention on padding token indices. Mask values selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>not masked</strong>,</li>
	<li>0 for tokens that are <strong>masked</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#attention-mask" rel="nofollow">What are attention masks?</a></li>
	</ul>`,name:"attention_mask"},{anchor:"optimum.intel.OVModelForQuestionAnswering.forward.token_type_ids",description:`<strong>token_type_ids</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Segment token indices to indicate first and second portions of the inputs. Indices are selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>sentence A</strong>,</li>
	<li>0 for tokens that are <strong>sentence B</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#token-type-ids" rel="nofollow">What are token type IDs?</a></li>
	</ul>`,name:"token_type_ids"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L226"}}),$t=new le({props:{$$slots:{default:[pc]},$$scope:{ctx:p}}}),Tt=new Y({props:{anchor:"optimum.intel.OVModelForQuestionAnswering.forward.example",$$slots:{default:[mc]},$$scope:{ctx:p}}}),yn=new G({props:{title:"OVModelForSequenceClassification",local:"optimum.intel.OVModelForSequenceClassification",headingTag:"h3"}}),_n=new I({props:{name:"class optimum.intel.OVModelForSequenceClassification",anchor:"optimum.intel.OVModelForSequenceClassification",parameters:[{name:"model",val:" = None"},{name:"config",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForSequenceClassification.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForSequenceClassification.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForSequenceClassification.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForSequenceClassification.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForSequenceClassification.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForSequenceClassification.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L154"}}),Mn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForSequenceClassification.forward",parameters:[{name:"input_ids",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"attention_mask",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"token_type_ids",val:": typing.Union[torch.Tensor, numpy.ndarray, NoneType] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForSequenceClassification.forward.input_ids",description:`<strong>input_ids</strong> (<code>torch.Tensor</code>) —
	Indices of input sequence tokens in the vocabulary.
	Indices can be obtained using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autotokenizer" rel="nofollow"><code>AutoTokenizer</code></a>.
	<a href="https://huggingface.co/docs/transformers/glossary#input-ids" rel="nofollow">What are input IDs?</a>`,name:"input_ids"},{anchor:"optimum.intel.OVModelForSequenceClassification.forward.attention_mask",description:`<strong>attention_mask</strong> (<code>torch.Tensor</code>), <em>optional</em>) —
	Mask to avoid performing attention on padding token indices. Mask values selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>not masked</strong>,</li>
	<li>0 for tokens that are <strong>masked</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#attention-mask" rel="nofollow">What are attention masks?</a></li>
	</ul>`,name:"attention_mask"},{anchor:"optimum.intel.OVModelForSequenceClassification.forward.token_type_ids",description:`<strong>token_type_ids</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Segment token indices to indicate first and second portions of the inputs. Indices are selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>sentence A</strong>,</li>
	<li>0 for tokens that are <strong>sentence B</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#token-type-ids" rel="nofollow">What are token type IDs?</a></li>
	</ul>`,name:"token_type_ids"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L161"}}),kt=new le({props:{$$slots:{default:[uc]},$$scope:{ctx:p}}}),Vt=new Y({props:{anchor:"optimum.intel.OVModelForSequenceClassification.forward.example",$$slots:{default:[gc]},$$scope:{ctx:p}}}),wn=new G({props:{title:"OVModelForTokenClassification",local:"optimum.intel.OVModelForTokenClassification",headingTag:"h3"}}),$n=new I({props:{name:"class optimum.intel.OVModelForTokenClassification",anchor:"optimum.intel.OVModelForTokenClassification",parameters:[{name:"model",val:" = None"},{name:"config",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForTokenClassification.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForTokenClassification.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForTokenClassification.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForTokenClassification.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForTokenClassification.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForTokenClassification.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L288"}}),Tn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForTokenClassification.forward",parameters:[{name:"input_ids",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"attention_mask",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"token_type_ids",val:": typing.Union[torch.Tensor, numpy.ndarray, NoneType] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForTokenClassification.forward.input_ids",description:`<strong>input_ids</strong> (<code>torch.Tensor</code>) —
	Indices of input sequence tokens in the vocabulary.
	Indices can be obtained using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autotokenizer" rel="nofollow"><code>AutoTokenizer</code></a>.
	<a href="https://huggingface.co/docs/transformers/glossary#input-ids" rel="nofollow">What are input IDs?</a>`,name:"input_ids"},{anchor:"optimum.intel.OVModelForTokenClassification.forward.attention_mask",description:`<strong>attention_mask</strong> (<code>torch.Tensor</code>), <em>optional</em>) —
	Mask to avoid performing attention on padding token indices. Mask values selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>not masked</strong>,</li>
	<li>0 for tokens that are <strong>masked</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#attention-mask" rel="nofollow">What are attention masks?</a></li>
	</ul>`,name:"attention_mask"},{anchor:"optimum.intel.OVModelForTokenClassification.forward.token_type_ids",description:`<strong>token_type_ids</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Segment token indices to indicate first and second portions of the inputs. Indices are selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>sentence A</strong>,</li>
	<li>0 for tokens that are <strong>sentence B</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#token-type-ids" rel="nofollow">What are token type IDs?</a></li>
	</ul>`,name:"token_type_ids"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L295"}}),Ct=new le({props:{$$slots:{default:[fc]},$$scope:{ctx:p}}}),Jt=new Y({props:{anchor:"optimum.intel.OVModelForTokenClassification.forward.example",$$slots:{default:[hc]},$$scope:{ctx:p}}}),kn=new G({props:{title:"Audio",local:"audio",headingTag:"h2"}}),Cn=new G({props:{title:"OVModelForAudioClassification",local:"optimum.intel.OVModelForAudioClassification",headingTag:"h3"}}),Jn=new I({props:{name:"class optimum.intel.OVModelForAudioClassification",anchor:"optimum.intel.OVModelForAudioClassification",parameters:[{name:"model",val:" = None"},{name:"config",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForAudioClassification.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForAudioClassification.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForAudioClassification.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForAudioClassification.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForAudioClassification.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForAudioClassification.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L651"}}),jn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForAudioClassification.forward",parameters:[{name:"input_values",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"attention_mask",val:": typing.Union[torch.Tensor, numpy.ndarray, NoneType] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForAudioClassification.forward.input_ids",description:`<strong>input_ids</strong> (<code>torch.Tensor</code>) —
	Indices of input sequence tokens in the vocabulary.
	Indices can be obtained using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autotokenizer" rel="nofollow"><code>AutoTokenizer</code></a>.
	<a href="https://huggingface.co/docs/transformers/glossary#input-ids" rel="nofollow">What are input IDs?</a>`,name:"input_ids"},{anchor:"optimum.intel.OVModelForAudioClassification.forward.attention_mask",description:`<strong>attention_mask</strong> (<code>torch.Tensor</code>), <em>optional</em>) —
	Mask to avoid performing attention on padding token indices. Mask values selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>not masked</strong>,</li>
	<li>0 for tokens that are <strong>masked</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#attention-mask" rel="nofollow">What are attention masks?</a></li>
	</ul>`,name:"attention_mask"},{anchor:"optimum.intel.OVModelForAudioClassification.forward.token_type_ids",description:`<strong>token_type_ids</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Segment token indices to indicate first and second portions of the inputs. Indices are selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>sentence A</strong>,</li>
	<li>0 for tokens that are <strong>sentence B</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#token-type-ids" rel="nofollow">What are token type IDs?</a></li>
	</ul>`,name:"token_type_ids"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L658"}}),jt=new le({props:{$$slots:{default:[vc]},$$scope:{ctx:p}}}),Ft=new Y({props:{anchor:"optimum.intel.OVModelForAudioClassification.forward.example",$$slots:{default:[bc]},$$scope:{ctx:p}}}),Fn=new G({props:{title:"OVModelForAudioFrameClassification",local:"optimum.intel.OVModelForAudioFrameClassification",headingTag:"h3"}}),xn=new I({props:{name:"class optimum.intel.OVModelForAudioFrameClassification",anchor:"optimum.intel.OVModelForAudioFrameClassification",parameters:[{name:"model",val:": Model"},{name:"config",val:": PreTrainedConfig = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForAudioFrameClassification.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForAudioFrameClassification.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForAudioFrameClassification.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForAudioFrameClassification.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForAudioFrameClassification.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForAudioFrameClassification.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L879"}}),On=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForAudioFrameClassification.forward",parameters:[{name:"input_values",val:": typing.Optional[torch.Tensor] = None"},{name:"attention_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForAudioFrameClassification.forward.input_values",description:`<strong>input_values</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, sequence_length)</code>) —
	Float values of input raw speech waveform..
	Input values can be obtained from audio file loaded into an array using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autofeatureextractor" rel="nofollow"><code>AutoFeatureExtractor</code></a>.`,name:"input_values"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L887"}}),xt=new le({props:{$$slots:{default:[yc]},$$scope:{ctx:p}}}),Ot=new Y({props:{anchor:"optimum.intel.OVModelForAudioFrameClassification.forward.example",$$slots:{default:[_c]},$$scope:{ctx:p}}}),Zn=new G({props:{title:"OVModelForCTC",local:"optimum.intel.OVModelForCTC",headingTag:"h3"}}),Un=new I({props:{name:"class optimum.intel.OVModelForCTC",anchor:"optimum.intel.OVModelForCTC",parameters:[{name:"model",val:": Model"},{name:"config",val:": PreTrainedConfig = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForCTC.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForCTC.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForCTC.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForCTC.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForCTC.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForCTC.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L723"}}),In=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForCTC.forward",parameters:[{name:"input_values",val:": typing.Optional[torch.Tensor] = None"},{name:"attention_mask",val:": typing.Union[torch.Tensor, numpy.ndarray, NoneType] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForCTC.forward.input_values",description:`<strong>input_values</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, sequence_length)</code>) —
	Float values of input raw speech waveform..
	Input values can be obtained from audio file loaded into an array using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autofeatureextractor" rel="nofollow"><code>AutoFeatureExtractor</code></a>.`,name:"input_values"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L731"}}),Zt=new le({props:{$$slots:{default:[Mc]},$$scope:{ctx:p}}}),Ut=new Y({props:{anchor:"optimum.intel.OVModelForCTC.forward.example",$$slots:{default:[wc]},$$scope:{ctx:p}}}),Nn=new G({props:{title:"OVModelForAudioXVector",local:"optimum.intel.OVModelForAudioXVector",headingTag:"h3"}}),Wn=new I({props:{name:"class optimum.intel.OVModelForAudioXVector",anchor:"optimum.intel.OVModelForAudioXVector",parameters:[{name:"model",val:": Model"},{name:"config",val:": PreTrainedConfig = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForAudioXVector.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForAudioXVector.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForAudioXVector.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForAudioXVector.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForAudioXVector.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForAudioXVector.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L803"}}),qn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForAudioXVector.forward",parameters:[{name:"input_values",val:": typing.Optional[torch.Tensor] = None"},{name:"attention_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForAudioXVector.forward.input_values",description:`<strong>input_values</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, sequence_length)</code>) —
	Float values of input raw speech waveform..
	Input values can be obtained from audio file loaded into an array using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autofeatureextractor" rel="nofollow"><code>AutoFeatureExtractor</code></a>.`,name:"input_values"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L811"}}),It=new le({props:{$$slots:{default:[$c]},$$scope:{ctx:p}}}),Nt=new Y({props:{anchor:"optimum.intel.OVModelForAudioXVector.forward.example",$$slots:{default:[Tc]},$$scope:{ctx:p}}}),Gn=new G({props:{title:"OVModelForSpeechSeq2Seq",local:"optimum.intel.OVModelForSpeechSeq2Seq",headingTag:"h3"}}),Xn=new I({props:{name:"class optimum.intel.OVModelForSpeechSeq2Seq",anchor:"optimum.intel.OVModelForSpeechSeq2Seq",parameters:[{name:"encoder",val:": Model"},{name:"decoder",val:": Model"},{name:"decoder_with_past",val:": Model = None"},{name:"config",val:": PreTrainedConfig = None"},{name:"device",val:": str = 'CPU'"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.encoder",description:`<strong>encoder</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the encoder.`,name:"encoder"},{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.decoder",description:`<strong>decoder</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the decoder.`,name:"decoder"},{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.decoder_with_past",description:`<strong>decoder_with_past</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the decoder with past key values.`,name:"decoder_with_past"},{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) —
	<a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is an instance of the configuration associated to the model. Initializing with a config file does
	not load the weights associated with the model, only the configuration.`,name:"config"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_seq2seq.py#L1246"}}),zn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForSpeechSeq2Seq.forward",parameters:[{name:"input_features",val:": typing.Optional[torch.FloatTensor] = None"},{name:"attention_mask",val:": typing.Optional[torch.LongTensor] = None"},{name:"decoder_input_ids",val:": typing.Optional[torch.LongTensor] = None"},{name:"decoder_attention_mask",val:": typing.Optional[torch.BoolTensor] = None"},{name:"encoder_outputs",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None"},{name:"past_key_values",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None"},{name:"cache_position",val:": typing.Optional[torch.LongTensor] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.forward.input_features",description:`<strong>input_features</strong> (<code>torch.FloatTensor</code>) —
	Mel features extracted from the raw speech waveform.
	<code>(batch_size, feature_size, encoder_sequence_length)</code>.`,name:"input_features"},{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.forward.decoder_input_ids",description:`<strong>decoder_input_ids</strong> (<code>torch.LongTensor</code>) —
	Indices of decoder input sequence tokens in the vocabulary of shape <code>(batch_size, decoder_sequence_length)</code>.`,name:"decoder_input_ids"},{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.forward.encoder_outputs",description:`<strong>encoder_outputs</strong> (<code>torch.FloatTensor</code>) —
	The encoder <code>last_hidden_state</code> of shape <code>(batch_size, encoder_sequence_length, hidden_size)</code>.`,name:"encoder_outputs"},{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.forward.past_key_values",description:`<strong>past_key_values</strong> (<code>tuple(tuple(torch.FloatTensor), optional, defaults to </code>None<code>)</code> —
	Contains the precomputed key and value hidden states of the attention blocks used to speed up decoding.
	The tuple is of length <code>config.n_layers</code> with each tuple having 2 tensors of shape
	<code>(batch_size, num_heads, decoder_sequence_length, embed_size_per_head)</code> and 2 additional tensors of shape
	<code>(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)</code>.`,name:"past_key_values"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_seq2seq.py#L1282"}}),Wt=new le({props:{$$slots:{default:[kc]},$$scope:{ctx:p}}}),qt=new Y({props:{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.forward.example",$$slots:{default:[Vc]},$$scope:{ctx:p}}}),Gt=new Y({props:{anchor:"optimum.intel.OVModelForSpeechSeq2Seq.forward.example-2",$$slots:{default:[Cc]},$$scope:{ctx:p}}}),Sn=new G({props:{title:"Computer Vision",local:"computer-vision",headingTag:"h2"}}),Rn=new G({props:{title:"OVModelForImageClassification",local:"optimum.intel.OVModelForImageClassification",headingTag:"h3"}}),Ln=new I({props:{name:"class optimum.intel.OVModelForImageClassification",anchor:"optimum.intel.OVModelForImageClassification",parameters:[{name:"model",val:" = None"},{name:"config",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForImageClassification.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForImageClassification.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForImageClassification.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForImageClassification.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForImageClassification.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForImageClassification.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L538"}}),En=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForImageClassification.forward",parameters:[{name:"pixel_values",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForImageClassification.forward.pixel_values",description:`<strong>pixel_values</strong> (<code>torch.Tensor</code>) —
	Pixel values corresponding to the images in the current batch.
	Pixel values can be obtained from encoded images using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autofeatureextractor" rel="nofollow"><code>AutoFeatureExtractor</code></a>.`,name:"pixel_values"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L600"}}),Xt=new le({props:{$$slots:{default:[Jc]},$$scope:{ctx:p}}}),zt=new Y({props:{anchor:"optimum.intel.OVModelForImageClassification.forward.example",$$slots:{default:[jc]},$$scope:{ctx:p}}}),St=new Y({props:{anchor:"optimum.intel.OVModelForImageClassification.forward.example-2",$$slots:{default:[Fc]},$$scope:{ctx:p}}}),Pn=new G({props:{title:"Multimodal",local:"multimodal",headingTag:"h2"}}),Qn=new G({props:{title:"OVModelForVision2Seq",local:"optimum.intel.OVModelForVision2Seq",headingTag:"h3"}}),Yn=new I({props:{name:"class optimum.intel.OVModelForVision2Seq",anchor:"optimum.intel.OVModelForVision2Seq",parameters:[{name:"encoder",val:": Model"},{name:"decoder",val:": Model"},{name:"decoder_with_past",val:": Model = None"},{name:"config",val:": PreTrainedConfig = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForVision2Seq.encoder",description:`<strong>encoder</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the encoder.`,name:"encoder"},{anchor:"optimum.intel.OVModelForVision2Seq.decoder",description:`<strong>decoder</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the decoder.`,name:"decoder"},{anchor:"optimum.intel.OVModelForVision2Seq.decoder_with_past",description:`<strong>decoder_with_past</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the decoder with past key values.`,name:"decoder_with_past"},{anchor:"optimum.intel.OVModelForVision2Seq.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) —
	<a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is an instance of the configuration associated to the model. Initializing with a config file does
	not load the weights associated with the model, only the configuration.`,name:"config"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_seq2seq.py#L1051"}}),Dn=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForVision2Seq.forward",parameters:[{name:"pixel_values",val:": typing.Optional[torch.FloatTensor] = None"},{name:"attention_mask",val:": typing.Optional[torch.LongTensor] = None"},{name:"decoder_input_ids",val:": typing.Optional[torch.LongTensor] = None"},{name:"decoder_attention_mask",val:": typing.Optional[torch.BoolTensor] = None"},{name:"encoder_outputs",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None"},{name:"past_key_values",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForVision2Seq.forward.pixel_values",description:`<strong>pixel_values</strong> (<code>torch.FloatTensor</code>) —
	Features extracted from an Image. This tensor should be of shape
	<code>(batch_size, num_channels, height, width)</code>.`,name:"pixel_values"},{anchor:"optimum.intel.OVModelForVision2Seq.forward.decoder_input_ids",description:`<strong>decoder_input_ids</strong> (<code>torch.LongTensor</code>) —
	Indices of decoder input sequence tokens in the vocabulary of shape <code>(batch_size, decoder_sequence_length)</code>.`,name:"decoder_input_ids"},{anchor:"optimum.intel.OVModelForVision2Seq.forward.encoder_outputs",description:`<strong>encoder_outputs</strong> (<code>torch.FloatTensor</code>) —
	The encoder <code>last_hidden_state</code> of shape <code>(batch_size, encoder_sequence_length, hidden_size)</code>.`,name:"encoder_outputs"},{anchor:"optimum.intel.OVModelForVision2Seq.forward.past_key_values",description:`<strong>past_key_values</strong> (<code>tuple(tuple(torch.FloatTensor), optional, defaults to </code>None<code>)</code> —
	Contains the precomputed key and value hidden states of the attention blocks used to speed up decoding.
	The tuple is of length <code>config.n_layers</code> with each tuple having 2 tensors of shape
	<code>(batch_size, num_heads, decoder_sequence_length, embed_size_per_head)</code> and 2 additional tensors of shape
	<code>(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)</code>.`,name:"past_key_values"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_seq2seq.py#L1105"}}),Bt=new le({props:{$$slots:{default:[xc]},$$scope:{ctx:p}}}),Rt=new Y({props:{anchor:"optimum.intel.OVModelForVision2Seq.forward.example",$$slots:{default:[Oc]},$$scope:{ctx:p}}}),Lt=new Y({props:{anchor:"optimum.intel.OVModelForVision2Seq.forward.example-2",$$slots:{default:[Zc]},$$scope:{ctx:p}}}),An=new G({props:{title:"OVModelForPix2Struct",local:"optimum.intel.OVModelForPix2Struct",headingTag:"h3"}}),Kn=new I({props:{name:"class optimum.intel.OVModelForPix2Struct",anchor:"optimum.intel.OVModelForPix2Struct",parameters:[{name:"encoder",val:": Model"},{name:"decoder",val:": Model"},{name:"decoder_with_past",val:": Model = None"},{name:"config",val:": PreTrainedConfig = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForPix2Struct.encoder",description:`<strong>encoder</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the encoder.`,name:"encoder"},{anchor:"optimum.intel.OVModelForPix2Struct.decoder",description:`<strong>decoder</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the decoder.`,name:"decoder"},{anchor:"optimum.intel.OVModelForPix2Struct.decoder_with_past",description:`<strong>decoder_with_past</strong> (<code>openvino.Model</code>) —
	The OpenVINO Runtime model associated to the decoder with past key values.`,name:"decoder_with_past"},{anchor:"optimum.intel.OVModelForPix2Struct.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) —
	<a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is an instance of the configuration associated to the model. Initializing with a config file does
	not load the weights associated with the model, only the configuration.`,name:"config"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_seq2seq.py#L1156"}}),eo=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForPix2Struct.forward",parameters:[{name:"flattened_patches",val:": typing.Optional[torch.FloatTensor] = None"},{name:"attention_mask",val:": typing.Optional[torch.LongTensor] = None"},{name:"decoder_input_ids",val:": typing.Optional[torch.LongTensor] = None"},{name:"decoder_attention_mask",val:": typing.Optional[torch.BoolTensor] = None"},{name:"encoder_outputs",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None"},{name:"past_key_values",val:": typing.Optional[typing.Tuple[typing.Tuple[torch.Tensor]]] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForPix2Struct.forward.flattened_patches",description:`<strong>flattened_patches</strong> (<code>torch.FloatTensor</code> of shape <code>(batch_size, seq_length, hidden_size)</code>) —
	Flattened pixel patches. the <code>hidden_size</code> is obtained by the following formula: <code>hidden_size</code> =
	<code>num_channels</code> <em> <code>patch_size</code> </em> <code>patch_size</code>
	The process of flattening the pixel patches is done by <code>Pix2StructProcessor</code>.`,name:"flattened_patches"},{anchor:"optimum.intel.OVModelForPix2Struct.forward.attention_mask",description:`<strong>attention_mask</strong> (<code>torch.FloatTensor</code> of shape <code>(batch_size, sequence_length)</code>, <em>optional</em>) —
	Mask to avoid performing attention on padding token indices.`,name:"attention_mask"},{anchor:"optimum.intel.OVModelForPix2Struct.forward.decoder_input_ids",description:`<strong>decoder_input_ids</strong> (<code>torch.LongTensor</code> of shape <code>(batch_size, target_sequence_length)</code>, <em>optional</em>) —
	Indices of decoder input sequence tokens in the vocabulary.
	Pix2StructText uses the <code>pad_token_id</code> as the starting token for <code>decoder_input_ids</code> generation. If
	<code>past_key_values</code> is used, optionally only the last <code>decoder_input_ids</code> have to be input (see
	<code>past_key_values</code>).`,name:"decoder_input_ids"},{anchor:"optimum.intel.OVModelForPix2Struct.forward.decoder_attention_mask",description:`<strong>decoder_attention_mask</strong> (<code>torch.BoolTensor</code> of shape <code>(batch_size, target_sequence_length)</code>, <em>optional</em>) —
	Default behavior: generate a tensor that ignores pad tokens in <code>decoder_input_ids</code>. Causal mask will also
	be used by default.`,name:"decoder_attention_mask"},{anchor:"optimum.intel.OVModelForPix2Struct.forward.encoder_outputs",description:`<strong>encoder_outputs</strong> (<code>tuple(tuple(torch.FloatTensor)</code>, <em>optional</em>) —
	Tuple consists of (<code>last_hidden_state</code>, <code>optional</code>: <em>hidden_states</em>, <code>optional</code>: <em>attentions</em>)
	<code>last_hidden_state</code> of shape <code>(batch_size, sequence_length, hidden_size)</code> is a sequence of hidden states at
	the output of the last layer of the encoder. Used in the cross-attention of the decoder.`,name:"encoder_outputs"},{anchor:"optimum.intel.OVModelForPix2Struct.forward.past_key_values",description:`<strong>past_key_values</strong> (<code>tuple(tuple(torch.FloatTensor), optional, defaults to </code>None<code>)</code> —
	Contains the precomputed key and value hidden states of the attention blocks used to speed up decoding.
	The tuple is of length <code>config.n_layers</code> with each tuple having 2 tensors of shape
	<code>(batch_size, num_heads, decoder_sequence_length, embed_size_per_head)</code> and 2 additional tensors of shape
	<code>(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)</code>.`,name:"past_key_values"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_seq2seq.py#L1196"}}),Et=new le({props:{$$slots:{default:[Uc]},$$scope:{ctx:p}}}),Pt=new Y({props:{anchor:"optimum.intel.OVModelForPix2Struct.forward.example",$$slots:{default:[Ic]},$$scope:{ctx:p}}}),to=new G({props:{title:"Custom Tasks",local:"custom-tasks",headingTag:"h2"}}),no=new G({props:{title:"OVModelForCustomTasks",local:"optimum.intel.OVModelForCustomTasks",headingTag:"h3"}}),oo=new I({props:{name:"class optimum.intel.OVModelForCustomTasks",anchor:"optimum.intel.OVModelForCustomTasks",parameters:[{name:"model",val:": Model"},{name:"config",val:": PreTrainedConfig = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForCustomTasks.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForCustomTasks.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForCustomTasks.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForCustomTasks.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForCustomTasks.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForCustomTasks.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L945"}}),so=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForCustomTasks.forward",parameters:[{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L946"}}),Ht=new le({props:{$$slots:{default:[Nc]},$$scope:{ctx:p}}}),Qt=new Y({props:{anchor:"optimum.intel.OVModelForCustomTasks.forward.example",$$slots:{default:[Wc]},$$scope:{ctx:p}}}),ao=new G({props:{title:"OVModelForFeatureExtraction",local:"optimum.intel.OVModelForFeatureExtraction",headingTag:"h3"}}),lo=new I({props:{name:"class optimum.intel.OVModelForFeatureExtraction",anchor:"optimum.intel.OVModelForFeatureExtraction",parameters:[{name:"model",val:" = None"},{name:"config",val:" = None"},{name:"kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForFeatureExtraction.model",description:"<strong>model</strong> (<code>openvino.Model</code>) — is the main class used to run OpenVINO Runtime inference.",name:"model"},{anchor:"optimum.intel.OVModelForFeatureExtraction.config",description:`<strong>config</strong> (<code>transformers.PretrainedConfig</code>) — <a href="https://huggingface.co/docs/transformers/main_classes/configuration#transformers.PretrainedConfig" rel="nofollow">PretrainedConfig</a>
	is the Model configuration class with all the parameters of the model.
	Initializing with a config file does not load the weights associated with the model, only the configuration.
	Check out the <code>~intel.openvino.modeling.OVBaseModel.from_pretrained</code> method to load the model weights.`,name:"config"},{anchor:"optimum.intel.OVModelForFeatureExtraction.device",description:`<strong>device</strong> (<code>str</code>, defaults to <code>"CPU"</code>) —
	The device type for which the model will be optimized for. The resulting compiled model will contains nodes specific to this device.`,name:"device"},{anchor:"optimum.intel.OVModelForFeatureExtraction.dynamic_shapes",description:`<strong>dynamic_shapes</strong> (<code>bool</code>, defaults to <code>True</code>) —
	All the model’s dimension will be set to dynamic when set to <code>True</code>. Should be set to <code>False</code> for the model to not be dynamically reshaped by default.`,name:"dynamic_shapes"},{anchor:"optimum.intel.OVModelForFeatureExtraction.ov_config",description:`<strong>ov_config</strong> (<code>Optional[Dict]</code>, defaults to <code>None</code>) —
	The dictionary containing the information related to the model compilation.`,name:"ov_config"},{anchor:"optimum.intel.OVModelForFeatureExtraction.compile",description:`<strong>compile</strong> (<code>bool</code>, defaults to <code>True</code>) —
	Disable the model compilation during the loading step when set to <code>False</code>.
	Can be useful to avoid unnecessary compilation, in the case where the model needs to be statically reshaped, the device modified or if FP16 conversion is enabled.`,name:"compile"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L352"}}),io=new I({props:{name:"forward",anchor:"optimum.intel.OVModelForFeatureExtraction.forward",parameters:[{name:"input_ids",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"attention_mask",val:": typing.Union[torch.Tensor, numpy.ndarray]"},{name:"token_type_ids",val:": typing.Union[torch.Tensor, numpy.ndarray, NoneType] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"optimum.intel.OVModelForFeatureExtraction.forward.input_ids",description:`<strong>input_ids</strong> (<code>torch.Tensor</code>) —
	Indices of input sequence tokens in the vocabulary.
	Indices can be obtained using <a href="https://huggingface.co/docs/transformers/autoclass_tutorial#autotokenizer" rel="nofollow"><code>AutoTokenizer</code></a>.
	<a href="https://huggingface.co/docs/transformers/glossary#input-ids" rel="nofollow">What are input IDs?</a>`,name:"input_ids"},{anchor:"optimum.intel.OVModelForFeatureExtraction.forward.attention_mask",description:`<strong>attention_mask</strong> (<code>torch.Tensor</code>), <em>optional</em>) —
	Mask to avoid performing attention on padding token indices. Mask values selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>not masked</strong>,</li>
	<li>0 for tokens that are <strong>masked</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#attention-mask" rel="nofollow">What are attention masks?</a></li>
	</ul>`,name:"attention_mask"},{anchor:"optimum.intel.OVModelForFeatureExtraction.forward.token_type_ids",description:`<strong>token_type_ids</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Segment token indices to indicate first and second portions of the inputs. Indices are selected in <code>[0, 1]</code>:
	<ul>
	<li>1 for tokens that are <strong>sentence A</strong>,</li>
	<li>0 for tokens that are <strong>sentence B</strong>.
	<a href="https://huggingface.co/docs/transformers/glossary#token-type-ids" rel="nofollow">What are token type IDs?</a></li>
	</ul>`,name:"token_type_ids"}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling.py#L366"}}),Yt=new le({props:{$$slots:{default:[qc]},$$scope:{ctx:p}}}),Dt=new Y({props:{anchor:"optimum.intel.OVModelForFeatureExtraction.forward.example",$$slots:{default:[Gc]},$$scope:{ctx:p}}}),ro=new G({props:{title:"Text-to-image",local:"text-to-image",headingTag:"h2"}}),co=new G({props:{title:"OVStableDiffusionPipeline",local:"optimum.intel.OVStableDiffusionPipeline",headingTag:"h3"}}),po=new I({props:{name:"class optimum.intel.OVStableDiffusionPipeline",anchor:"optimum.intel.OVStableDiffusionPipeline",parameters:[{name:"scheduler",val:": SchedulerMixin"},{name:"unet",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_decoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_2",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_3",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"transformer",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"tokenizer",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_2",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_3",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"feature_extractor",val:": typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] = None"},{name:"force_zeros_for_empty_prompt",val:": bool = True"},{name:"requires_aesthetics_score",val:": bool = False"},{name:"add_watermarker",val:": typing.Optional[bool] = None"},{name:"device",val:": str = 'CPU'"},{name:"compile",val:": bool = True"},{name:"compile_only",val:": bool = False"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict, NoneType] = None"},{name:"*kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_diffusion.py#L1443"}}),mo=new I({props:{name:"forward",anchor:"optimum.intel.OVStableDiffusionPipeline.forward",parameters:[{name:"args",val:""},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L976"}}),uo=new G({props:{title:"OVStableDiffusionXLPipeline",local:"optimum.intel.OVStableDiffusionXLPipeline",headingTag:"h3"}}),go=new I({props:{name:"class optimum.intel.OVStableDiffusionXLPipeline",anchor:"optimum.intel.OVStableDiffusionXLPipeline",parameters:[{name:"scheduler",val:": SchedulerMixin"},{name:"unet",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_decoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_2",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_3",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"transformer",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"tokenizer",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_2",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_3",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"feature_extractor",val:": typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] = None"},{name:"force_zeros_for_empty_prompt",val:": bool = True"},{name:"requires_aesthetics_score",val:": bool = False"},{name:"add_watermarker",val:": typing.Optional[bool] = None"},{name:"device",val:": str = 'CPU'"},{name:"compile",val:": bool = True"},{name:"compile_only",val:": bool = False"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict, NoneType] = None"},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_diffusion.py#L1477"}}),fo=new I({props:{name:"forward",anchor:"optimum.intel.OVStableDiffusionXLPipeline.forward",parameters:[{name:"args",val:""},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L976"}}),ho=new G({props:{title:"OVLatentConsistencyModelPipeline",local:"optimum.intel.OVLatentConsistencyModelPipeline",headingTag:"h3"}}),vo=new I({props:{name:"class optimum.intel.OVLatentConsistencyModelPipeline",anchor:"optimum.intel.OVLatentConsistencyModelPipeline",parameters:[{name:"scheduler",val:": SchedulerMixin"},{name:"unet",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_decoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_2",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_3",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"transformer",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"tokenizer",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_2",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_3",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"feature_extractor",val:": typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] = None"},{name:"force_zeros_for_empty_prompt",val:": bool = True"},{name:"requires_aesthetics_score",val:": bool = False"},{name:"add_watermarker",val:": typing.Optional[bool] = None"},{name:"device",val:": str = 'CPU'"},{name:"compile",val:": bool = True"},{name:"compile_only",val:": bool = False"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict, NoneType] = None"},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_diffusion.py#L1578"}}),bo=new I({props:{name:"forward",anchor:"optimum.intel.OVLatentConsistencyModelPipeline.forward",parameters:[{name:"args",val:""},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L976"}}),yo=new G({props:{title:"Image-to-image",local:"image-to-image",headingTag:"h2"}}),_o=new G({props:{title:"OVStableDiffusionImg2ImgPipeline",local:"optimum.intel.OVStableDiffusionImg2ImgPipeline",headingTag:"h3"}}),Mo=new I({props:{name:"class optimum.intel.OVStableDiffusionImg2ImgPipeline",anchor:"optimum.intel.OVStableDiffusionImg2ImgPipeline",parameters:[{name:"scheduler",val:": SchedulerMixin"},{name:"unet",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_decoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_2",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_3",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"transformer",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"tokenizer",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_2",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_3",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"feature_extractor",val:": typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] = None"},{name:"force_zeros_for_empty_prompt",val:": bool = True"},{name:"requires_aesthetics_score",val:": bool = False"},{name:"add_watermarker",val:": typing.Optional[bool] = None"},{name:"device",val:": str = 'CPU'"},{name:"compile",val:": bool = True"},{name:"compile_only",val:": bool = False"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict, NoneType] = None"},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_diffusion.py#L1453"}}),wo=new I({props:{name:"forward",anchor:"optimum.intel.OVStableDiffusionImg2ImgPipeline.forward",parameters:[{name:"args",val:""},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L976"}}),$o=new G({props:{title:"OVStableDiffusionXLImg2ImgPipeline",local:"optimum.intel.OVStableDiffusionXLImg2ImgPipeline",headingTag:"h3"}}),To=new I({props:{name:"class optimum.intel.OVStableDiffusionXLImg2ImgPipeline",anchor:"optimum.intel.OVStableDiffusionXLImg2ImgPipeline",parameters:[{name:"scheduler",val:": SchedulerMixin"},{name:"unet",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_decoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_2",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_3",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"transformer",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"tokenizer",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_2",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_3",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"feature_extractor",val:": typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] = None"},{name:"force_zeros_for_empty_prompt",val:": bool = True"},{name:"requires_aesthetics_score",val:": bool = False"},{name:"add_watermarker",val:": typing.Optional[bool] = None"},{name:"device",val:": str = 'CPU'"},{name:"compile",val:": bool = True"},{name:"compile_only",val:": bool = False"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict, NoneType] = None"},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_diffusion.py#L1500"}}),ko=new I({props:{name:"forward",anchor:"optimum.intel.OVStableDiffusionXLImg2ImgPipeline.forward",parameters:[{name:"args",val:""},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L976"}}),Vo=new G({props:{title:"Inpainting",local:"inpainting",headingTag:"h2"}}),Co=new G({props:{title:"OVStableDiffusionInpaintPipeline",local:"optimum.intel.OVStableDiffusionInpaintPipeline",headingTag:"h3"}}),Jo=new I({props:{name:"class optimum.intel.OVStableDiffusionInpaintPipeline",anchor:"optimum.intel.OVStableDiffusionInpaintPipeline",parameters:[{name:"scheduler",val:": SchedulerMixin"},{name:"unet",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_decoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"vae_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_2",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"text_encoder_3",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"transformer",val:": typing.Optional[openvino._ov_api.Model] = None"},{name:"tokenizer",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_2",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"tokenizer_3",val:": typing.Optional[transformers.models.clip.tokenization_clip.CLIPTokenizer] = None"},{name:"feature_extractor",val:": typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] = None"},{name:"force_zeros_for_empty_prompt",val:": bool = True"},{name:"requires_aesthetics_score",val:": bool = False"},{name:"add_watermarker",val:": typing.Optional[bool] = None"},{name:"device",val:": str = 'CPU'"},{name:"compile",val:": bool = True"},{name:"compile_only",val:": bool = False"},{name:"dynamic_shapes",val:": bool = True"},{name:"ov_config",val:": typing.Optional[typing.Dict[str, str]] = None"},{name:"model_save_dir",val:": typing.Union[str, pathlib.Path, optimum.intel.openvino.utils.TemporaryDirectory, NoneType] = None"},{name:"quantization_config",val:": typing.Union[optimum.intel.openvino.configuration.OVWeightQuantizationConfig, typing.Dict, NoneType] = None"},{name:"kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_diffusion.py#L1465"}}),jo=new I({props:{name:"forward",anchor:"optimum.intel.OVStableDiffusionInpaintPipeline.forward",parameters:[{name:"args",val:""},{name:"*kwargs",val:""}],source:"https://github.com/huggingface/optimum-intel/blob/vr_1684/optimum/intel/openvino/modeling_base.py#L976"}}),{c(){t=g("meta"),a=r(),o=g("p"),s=r(),_(m.$$.fragment),n=r(),_(c.$$.fragment),x=r(),_(J.$$.fragment),j=r(),v=g("div"),_(k.$$.fragment),V=r(),T=g("p"),T.textContent=O,W=r(),z=g("div"),_(S.$$.fragment),ee=r(),te=g("p"),te.textContent=P,E=r(),B=g("div"),_(X.$$.fragment),R=r(),L=g("p"),L.textContent=Q,N=r(),_(U.$$.fragment),H=r(),A=g("p"),A.textContent=K,Oo=r(),_(an.$$.fragment),Ds=r(),ne=g("div"),_(ln.$$.fragment),al=r(),Zo=g("p"),Zo.textContent=ir,ll=r(),Uo=g("p"),Uo.innerHTML=rr,il=r(),Io=g("div"),_(rn.$$.fragment),rl=r(),No=g("div"),_(dn.$$.fragment),As=r(),_(cn.$$.fragment),Ks=r(),pe=g("div"),_(pn.$$.fragment),dl=r(),Wo=g("p"),Wo.textContent=dr,cl=r(),qo=g("p"),qo.innerHTML=cr,pl=r(),Ce=g("div"),_(mn.$$.fragment),ml=r(),Go=g("p"),Go.innerHTML=pr,ul=r(),_(bt.$$.fragment),gl=r(),_(yt.$$.fragment),ea=r(),_(un.$$.fragment),ta=r(),qe=g("div"),_(gn.$$.fragment),fl=r(),Xo=g("p"),Xo.textContent=mr,hl=r(),ie=g("div"),_(fn.$$.fragment),vl=r(),zo=g("p"),zo.innerHTML=ur,bl=r(),_(_t.$$.fragment),yl=r(),_(Mt.$$.fragment),_l=r(),_(wt.$$.fragment),na=r(),_(hn.$$.fragment),oa=r(),me=g("div"),_(vn.$$.fragment),Ml=r(),So=g("p"),So.textContent=gr,wl=r(),Bo=g("p"),Bo.innerHTML=fr,$l=r(),Je=g("div"),_(bn.$$.fragment),Tl=r(),Ro=g("p"),Ro.innerHTML=hr,kl=r(),_($t.$$.fragment),Vl=r(),_(Tt.$$.fragment),sa=r(),_(yn.$$.fragment),aa=r(),ue=g("div"),_(_n.$$.fragment),Cl=r(),Lo=g("p"),Lo.textContent=vr,Jl=r(),Eo=g("p"),Eo.innerHTML=br,jl=r(),je=g("div"),_(Mn.$$.fragment),Fl=r(),Po=g("p"),Po.innerHTML=yr,xl=r(),_(kt.$$.fragment),Ol=r(),_(Vt.$$.fragment),la=r(),_(wn.$$.fragment),ia=r(),ge=g("div"),_($n.$$.fragment),Zl=r(),Ho=g("p"),Ho.textContent=_r,Ul=r(),Qo=g("p"),Qo.innerHTML=Mr,Il=r(),Fe=g("div"),_(Tn.$$.fragment),Nl=r(),Yo=g("p"),Yo.innerHTML=wr,Wl=r(),_(Ct.$$.fragment),ql=r(),_(Jt.$$.fragment),ra=r(),_(kn.$$.fragment),da=r(),Vn=g("p"),Vn.textContent=$r,ca=r(),_(Cn.$$.fragment),pa=r(),fe=g("div"),_(Jn.$$.fragment),Gl=r(),Do=g("p"),Do.textContent=Tr,Xl=r(),Ao=g("p"),Ao.innerHTML=kr,zl=r(),xe=g("div"),_(jn.$$.fragment),Sl=r(),Ko=g("p"),Ko.innerHTML=Vr,Bl=r(),_(jt.$$.fragment),Rl=r(),_(Ft.$$.fragment),ma=r(),_(Fn.$$.fragment),ua=r(),oe=g("div"),_(xn.$$.fragment),Ll=r(),es=g("p"),es.textContent=Cr,El=r(),ts=g("p"),ts.innerHTML=Jr,Pl=r(),ns=g("p"),ns.textContent=jr,Hl=r(),Oe=g("div"),_(On.$$.fragment),Ql=r(),os=g("p"),os.innerHTML=Fr,Yl=r(),_(xt.$$.fragment),Dl=r(),_(Ot.$$.fragment),ga=r(),_(Zn.$$.fragment),fa=r(),se=g("div"),_(Un.$$.fragment),Al=r(),ss=g("p"),ss.textContent=xr,Kl=r(),as=g("p"),as.innerHTML=Or,ei=r(),ls=g("p"),ls.textContent=Zr,ti=r(),Ze=g("div"),_(In.$$.fragment),ni=r(),is=g("p"),is.innerHTML=Ur,oi=r(),_(Zt.$$.fragment),si=r(),_(Ut.$$.fragment),ha=r(),_(Nn.$$.fragment),va=r(),ae=g("div"),_(Wn.$$.fragment),ai=r(),rs=g("p"),rs.textContent=Ir,li=r(),ds=g("p"),ds.innerHTML=Nr,ii=r(),cs=g("p"),cs.textContent=Wr,ri=r(),Ue=g("div"),_(qn.$$.fragment),di=r(),ps=g("p"),ps.innerHTML=qr,ci=r(),_(It.$$.fragment),pi=r(),_(Nt.$$.fragment),ba=r(),_(Gn.$$.fragment),ya=r(),Ge=g("div"),_(Xn.$$.fragment),mi=r(),ms=g("p"),ms.textContent=Gr,ui=r(),re=g("div"),_(zn.$$.fragment),gi=r(),us=g("p"),us.innerHTML=Xr,fi=r(),_(Wt.$$.fragment),hi=r(),_(qt.$$.fragment),vi=r(),_(Gt.$$.fragment),_a=r(),_(Sn.$$.fragment),Ma=r(),Bn=g("p"),Bn.textContent=zr,wa=r(),_(Rn.$$.fragment),$a=r(),he=g("div"),_(Ln.$$.fragment),bi=r(),gs=g("p"),gs.textContent=Sr,yi=r(),fs=g("p"),fs.innerHTML=Br,_i=r(),de=g("div"),_(En.$$.fragment),Mi=r(),hs=g("p"),hs.innerHTML=Rr,wi=r(),_(Xt.$$.fragment),$i=r(),_(zt.$$.fragment),Ti=en(`
	This class can also be used with [timm](https://github.com/huggingface/pytorch-image-models)
	`),_(St.$$.fragment),Ta=r(),_(Pn.$$.fragment),ka=r(),Hn=g("p"),Hn.textContent=Lr,Va=r(),_(Qn.$$.fragment),Ca=r(),Xe=g("div"),_(Yn.$$.fragment),ki=r(),vs=g("p"),vs.textContent=Er,Vi=r(),ce=g("div"),_(Dn.$$.fragment),Ci=r(),bs=g("p"),bs.innerHTML=Pr,Ji=r(),_(Bt.$$.fragment),ji=r(),_(Rt.$$.fragment),Fi=r(),_(Lt.$$.fragment),Ja=r(),_(An.$$.fragment),ja=r(),ze=g("div"),_(Kn.$$.fragment),xi=r(),ys=g("p"),ys.textContent=Hr,Oi=r(),Ie=g("div"),_(eo.$$.fragment),Zi=r(),_s=g("p"),_s.innerHTML=Qr,Ui=r(),_(Et.$$.fragment),Ii=r(),_(Pt.$$.fragment),Fa=r(),_(to.$$.fragment),xa=r(),_(no.$$.fragment),Oa=r(),ve=g("div"),_(oo.$$.fragment),Ni=r(),Ms=g("p"),Ms.textContent=Yr,Wi=r(),ws=g("p"),ws.innerHTML=Dr,qi=r(),Ne=g("div"),_(so.$$.fragment),Gi=r(),$s=g("p"),$s.innerHTML=Ar,Xi=r(),_(Ht.$$.fragment),zi=r(),_(Qt.$$.fragment),Za=r(),_(ao.$$.fragment),Ua=r(),be=g("div"),_(lo.$$.fragment),Si=r(),Ts=g("p"),Ts.textContent=Kr,Bi=r(),ks=g("p"),ks.innerHTML=ed,Ri=r(),We=g("div"),_(io.$$.fragment),Li=r(),Vs=g("p"),Vs.innerHTML=td,Ei=r(),_(Yt.$$.fragment),Pi=r(),_(Dt.$$.fragment),Ia=r(),_(ro.$$.fragment),Na=r(),_(co.$$.fragment),Wa=r(),Se=g("div"),_(po.$$.fragment),Hi=r(),Cs=g("p"),Cs.innerHTML=nd,Qi=r(),Js=g("div"),_(mo.$$.fragment),qa=r(),_(uo.$$.fragment),Ga=r(),Be=g("div"),_(go.$$.fragment),Yi=r(),js=g("p"),js.innerHTML=od,Di=r(),Fs=g("div"),_(fo.$$.fragment),Xa=r(),_(ho.$$.fragment),za=r(),Re=g("div"),_(vo.$$.fragment),Ai=r(),xs=g("p"),xs.innerHTML=sd,Ki=r(),Os=g("div"),_(bo.$$.fragment),Sa=r(),_(yo.$$.fragment),Ba=r(),_(_o.$$.fragment),Ra=r(),Le=g("div"),_(Mo.$$.fragment),er=r(),Zs=g("p"),Zs.innerHTML=ad,tr=r(),Us=g("div"),_(wo.$$.fragment),La=r(),_($o.$$.fragment),Ea=r(),Ee=g("div"),_(To.$$.fragment),nr=r(),Is=g("p"),Is.innerHTML=ld,or=r(),Ns=g("div"),_(ko.$$.fragment),Pa=r(),_(Vo.$$.fragment),Ha=r(),_(Co.$$.fragment),Qa=r(),Pe=g("div"),_(Jo.$$.fragment),sr=r(),Ws=g("p"),Ws.innerHTML=id,ar=r(),qs=g("div"),_(jo.$$.fragment),Ya=r(),Ls=g("p"),this.h()},l(e){const u=Qd("svelte-u9bgzb",document.head);t=f(u,"META",{name:!0,content:!0}),u.forEach(l),a=d(e),o=f(e,"P",{}),Z(o).forEach(l),s=d(e),M(m.$$.fragment,e),n=d(e),M(c.$$.fragment,e),x=d(e),M(J.$$.fragment,e),j=d(e),v=f(e,"DIV",{class:!0});var He=Z(v);M(k.$$.fragment,He),V=d(He),T=f(He,"P",{"data-svelte-h":!0}),F(T)!=="svelte-1eh3zxn"&&(T.textContent=O),W=d(He),z=f(He,"DIV",{class:!0});var Fo=Z(z);M(S.$$.fragment,Fo),ee=d(Fo),te=f(Fo,"P",{"data-svelte-h":!0}),F(te)!=="svelte-18vxhwp"&&(te.textContent=P),Fo.forEach(l),E=d(He),B=f(He,"DIV",{class:!0});var xo=Z(B);M(X.$$.fragment,xo),R=d(xo),L=f(xo,"P",{"data-svelte-h":!0}),F(L)!=="svelte-zx8pbr"&&(L.textContent=Q),xo.forEach(l),He.forEach(l),N=d(e),M(U.$$.fragment,e),H=d(e),A=f(e,"P",{"data-svelte-h":!0}),F(A)!=="svelte-nv9auu"&&(A.textContent=K),Oo=d(e),M(an.$$.fragment,e),Ds=d(e),ne=f(e,"DIV",{class:!0});var ye=Z(ne);M(ln.$$.fragment,ye),al=d(ye),Zo=f(ye,"P",{"data-svelte-h":!0}),F(Zo)!=="svelte-1eb35zy"&&(Zo.textContent=ir),ll=d(ye),Uo=f(ye,"P",{"data-svelte-h":!0}),F(Uo)!=="svelte-6rqfag"&&(Uo.innerHTML=rr),il=d(ye),Io=f(ye,"DIV",{class:!0});var Es=Z(Io);M(rn.$$.fragment,Es),Es.forEach(l),rl=d(ye),No=f(ye,"DIV",{class:!0});var Ps=Z(No);M(dn.$$.fragment,Ps),Ps.forEach(l),ye.forEach(l),As=d(e),M(cn.$$.fragment,e),Ks=d(e),pe=f(e,"DIV",{class:!0});var Qe=Z(pe);M(pn.$$.fragment,Qe),dl=d(Qe),Wo=f(Qe,"P",{"data-svelte-h":!0}),F(Wo)!=="svelte-1hn3d6"&&(Wo.textContent=dr),cl=d(Qe),qo=f(Qe,"P",{"data-svelte-h":!0}),F(qo)!=="svelte-6rqfag"&&(qo.innerHTML=cr),pl=d(Qe),Ce=f(Qe,"DIV",{class:!0});var Ye=Z(Ce);M(mn.$$.fragment,Ye),ml=d(Ye),Go=f(Ye,"P",{"data-svelte-h":!0}),F(Go)!=="svelte-1dsm6s1"&&(Go.innerHTML=pr),ul=d(Ye),M(bt.$$.fragment,Ye),gl=d(Ye),M(yt.$$.fragment,Ye),Ye.forEach(l),Qe.forEach(l),ea=d(e),M(un.$$.fragment,e),ta=d(e),qe=f(e,"DIV",{class:!0});var mt=Z(qe);M(gn.$$.fragment,mt),fl=d(mt),Xo=f(mt,"P",{"data-svelte-h":!0}),F(Xo)!=="svelte-vogxny"&&(Xo.textContent=mr),hl=d(mt),ie=f(mt,"DIV",{class:!0});var _e=Z(ie);M(fn.$$.fragment,_e),vl=d(_e),zo=f(_e,"P",{"data-svelte-h":!0}),F(zo)!=="svelte-1mjwwl7"&&(zo.innerHTML=ur),bl=d(_e),M(_t.$$.fragment,_e),yl=d(_e),M(Mt.$$.fragment,_e),_l=d(_e),M(wt.$$.fragment,_e),_e.forEach(l),mt.forEach(l),na=d(e),M(hn.$$.fragment,e),oa=d(e),me=f(e,"DIV",{class:!0});var De=Z(me);M(vn.$$.fragment,De),Ml=d(De),So=f(De,"P",{"data-svelte-h":!0}),F(So)!=="svelte-m8bn61"&&(So.textContent=gr),wl=d(De),Bo=f(De,"P",{"data-svelte-h":!0}),F(Bo)!=="svelte-6rqfag"&&(Bo.innerHTML=fr),$l=d(De),Je=f(De,"DIV",{class:!0});var Ae=Z(Je);M(bn.$$.fragment,Ae),Tl=d(Ae),Ro=f(Ae,"P",{"data-svelte-h":!0}),F(Ro)!=="svelte-1f6p2o3"&&(Ro.innerHTML=hr),kl=d(Ae),M($t.$$.fragment,Ae),Vl=d(Ae),M(Tt.$$.fragment,Ae),Ae.forEach(l),De.forEach(l),sa=d(e),M(yn.$$.fragment,e),aa=d(e),ue=f(e,"DIV",{class:!0});var Ke=Z(ue);M(_n.$$.fragment,Ke),Cl=d(Ke),Lo=f(Ke,"P",{"data-svelte-h":!0}),F(Lo)!=="svelte-3sxcf5"&&(Lo.textContent=vr),Jl=d(Ke),Eo=f(Ke,"P",{"data-svelte-h":!0}),F(Eo)!=="svelte-6rqfag"&&(Eo.innerHTML=br),jl=d(Ke),je=f(Ke,"DIV",{class:!0});var et=Z(je);M(Mn.$$.fragment,et),Fl=d(et),Po=f(et,"P",{"data-svelte-h":!0}),F(Po)!=="svelte-fxv4d7"&&(Po.innerHTML=yr),xl=d(et),M(kt.$$.fragment,et),Ol=d(et),M(Vt.$$.fragment,et),et.forEach(l),Ke.forEach(l),la=d(e),M(wn.$$.fragment,e),ia=d(e),ge=f(e,"DIV",{class:!0});var tt=Z(ge);M($n.$$.fragment,tt),Zl=d(tt),Ho=f(tt,"P",{"data-svelte-h":!0}),F(Ho)!=="svelte-2r9afx"&&(Ho.textContent=_r),Ul=d(tt),Qo=f(tt,"P",{"data-svelte-h":!0}),F(Qo)!=="svelte-6rqfag"&&(Qo.innerHTML=Mr),Il=d(tt),Fe=f(tt,"DIV",{class:!0});var nt=Z(Fe);M(Tn.$$.fragment,nt),Nl=d(nt),Yo=f(nt,"P",{"data-svelte-h":!0}),F(Yo)!=="svelte-9czh8b"&&(Yo.innerHTML=wr),Wl=d(nt),M(Ct.$$.fragment,nt),ql=d(nt),M(Jt.$$.fragment,nt),nt.forEach(l),tt.forEach(l),ra=d(e),M(kn.$$.fragment,e),da=d(e),Vn=f(e,"P",{"data-svelte-h":!0}),F(Vn)!=="svelte-ib9qfo"&&(Vn.textContent=$r),ca=d(e),M(Cn.$$.fragment,e),pa=d(e),fe=f(e,"DIV",{class:!0});var ot=Z(fe);M(Jn.$$.fragment,ot),Gl=d(ot),Do=f(ot,"P",{"data-svelte-h":!0}),F(Do)!=="svelte-qq0ezu"&&(Do.textContent=Tr),Xl=d(ot),Ao=f(ot,"P",{"data-svelte-h":!0}),F(Ao)!=="svelte-6rqfag"&&(Ao.innerHTML=kr),zl=d(ot),xe=f(ot,"DIV",{class:!0});var st=Z(xe);M(jn.$$.fragment,st),Sl=d(st),Ko=f(st,"P",{"data-svelte-h":!0}),F(Ko)!=="svelte-14zayab"&&(Ko.innerHTML=Vr),Bl=d(st),M(jt.$$.fragment,st),Rl=d(st),M(Ft.$$.fragment,st),st.forEach(l),ot.forEach(l),ma=d(e),M(Fn.$$.fragment,e),ua=d(e),oe=f(e,"DIV",{class:!0});var Me=Z(oe);M(xn.$$.fragment,Me),Ll=d(Me),es=f(Me,"P",{"data-svelte-h":!0}),F(es)!=="svelte-f1dmx9"&&(es.textContent=Cr),El=d(Me),ts=f(Me,"P",{"data-svelte-h":!0}),F(ts)!=="svelte-6rqfag"&&(ts.innerHTML=Jr),Pl=d(Me),ns=f(Me,"P",{"data-svelte-h":!0}),F(ns)!=="svelte-1l1oz51"&&(ns.textContent=jr),Hl=d(Me),Oe=f(Me,"DIV",{class:!0});var at=Z(Oe);M(On.$$.fragment,at),Ql=d(at),os=f(at,"P",{"data-svelte-h":!0}),F(os)!=="svelte-1i8gz5r"&&(os.innerHTML=Fr),Yl=d(at),M(xt.$$.fragment,at),Dl=d(at),M(Ot.$$.fragment,at),at.forEach(l),Me.forEach(l),ga=d(e),M(Zn.$$.fragment,e),fa=d(e),se=f(e,"DIV",{class:!0});var we=Z(se);M(Un.$$.fragment,we),Al=d(we),ss=f(we,"P",{"data-svelte-h":!0}),F(ss)!=="svelte-rhfujk"&&(ss.textContent=xr),Kl=d(we),as=f(we,"P",{"data-svelte-h":!0}),F(as)!=="svelte-6rqfag"&&(as.innerHTML=Or),ei=d(we),ls=f(we,"P",{"data-svelte-h":!0}),F(ls)!=="svelte-7q8vvu"&&(ls.textContent=Zr),ti=d(we),Ze=f(we,"DIV",{class:!0});var lt=Z(Ze);M(In.$$.fragment,lt),ni=d(lt),is=f(lt,"P",{"data-svelte-h":!0}),F(is)!=="svelte-lnyw5n"&&(is.innerHTML=Ur),oi=d(lt),M(Zt.$$.fragment,lt),si=d(lt),M(Ut.$$.fragment,lt),lt.forEach(l),we.forEach(l),ha=d(e),M(Nn.$$.fragment,e),va=d(e),ae=f(e,"DIV",{class:!0});var $e=Z(ae);M(Wn.$$.fragment,$e),ai=d($e),rs=f($e,"P",{"data-svelte-h":!0}),F(rs)!=="svelte-1p03umf"&&(rs.textContent=Ir),li=d($e),ds=f($e,"P",{"data-svelte-h":!0}),F(ds)!=="svelte-6rqfag"&&(ds.innerHTML=Nr),ii=d($e),cs=f($e,"P",{"data-svelte-h":!0}),F(cs)!=="svelte-15ng2dj"&&(cs.textContent=Wr),ri=d($e),Ue=f($e,"DIV",{class:!0});var it=Z(Ue);M(qn.$$.fragment,it),di=d(it),ps=f(it,"P",{"data-svelte-h":!0}),F(ps)!=="svelte-1tz61kr"&&(ps.innerHTML=qr),ci=d(it),M(It.$$.fragment,it),pi=d(it),M(Nt.$$.fragment,it),it.forEach(l),$e.forEach(l),ba=d(e),M(Gn.$$.fragment,e),ya=d(e),Ge=f(e,"DIV",{class:!0});var ut=Z(Ge);M(Xn.$$.fragment,ut),mi=d(ut),ms=f(ut,"P",{"data-svelte-h":!0}),F(ms)!=="svelte-gg5e9y"&&(ms.textContent=Gr),ui=d(ut),re=f(ut,"DIV",{class:!0});var Te=Z(re);M(zn.$$.fragment,Te),gi=d(Te),us=f(Te,"P",{"data-svelte-h":!0}),F(us)!=="svelte-b3ky9r"&&(us.innerHTML=Xr),fi=d(Te),M(Wt.$$.fragment,Te),hi=d(Te),M(qt.$$.fragment,Te),vi=d(Te),M(Gt.$$.fragment,Te),Te.forEach(l),ut.forEach(l),_a=d(e),M(Sn.$$.fragment,e),Ma=d(e),Bn=f(e,"P",{"data-svelte-h":!0}),F(Bn)!=="svelte-rd7k31"&&(Bn.textContent=zr),wa=d(e),M(Rn.$$.fragment,e),$a=d(e),he=f(e,"DIV",{class:!0});var rt=Z(he);M(Ln.$$.fragment,rt),bi=d(rt),gs=f(rt,"P",{"data-svelte-h":!0}),F(gs)!=="svelte-38to9p"&&(gs.textContent=Sr),yi=d(rt),fs=f(rt,"P",{"data-svelte-h":!0}),F(fs)!=="svelte-6rqfag"&&(fs.innerHTML=Br),_i=d(rt),de=f(rt,"DIV",{class:!0});var ke=Z(de);M(En.$$.fragment,ke),Mi=d(ke),hs=f(ke,"P",{"data-svelte-h":!0}),F(hs)!=="svelte-v2nbsr"&&(hs.innerHTML=Rr),wi=d(ke),M(Xt.$$.fragment,ke),$i=d(ke),M(zt.$$.fragment,ke),Ti=tn(ke,`
	This class can also be used with [timm](https://github.com/huggingface/pytorch-image-models)
	`),M(St.$$.fragment,ke),ke.forEach(l),rt.forEach(l),Ta=d(e),M(Pn.$$.fragment,e),ka=d(e),Hn=f(e,"P",{"data-svelte-h":!0}),F(Hn)!=="svelte-g0e6o0"&&(Hn.textContent=Lr),Va=d(e),M(Qn.$$.fragment,e),Ca=d(e),Xe=f(e,"DIV",{class:!0});var gt=Z(Xe);M(Yn.$$.fragment,gt),ki=d(gt),vs=f(gt,"P",{"data-svelte-h":!0}),F(vs)!=="svelte-19k7u3u"&&(vs.textContent=Er),Vi=d(gt),ce=f(gt,"DIV",{class:!0});var Ve=Z(ce);M(Dn.$$.fragment,Ve),Ci=d(Ve),bs=f(Ve,"P",{"data-svelte-h":!0}),F(bs)!=="svelte-11n0fhn"&&(bs.innerHTML=Pr),Ji=d(Ve),M(Bt.$$.fragment,Ve),ji=d(Ve),M(Rt.$$.fragment,Ve),Fi=d(Ve),M(Lt.$$.fragment,Ve),Ve.forEach(l),gt.forEach(l),Ja=d(e),M(An.$$.fragment,e),ja=d(e),ze=f(e,"DIV",{class:!0});var ft=Z(ze);M(Kn.$$.fragment,ft),xi=d(ft),ys=f(ft,"P",{"data-svelte-h":!0}),F(ys)!=="svelte-1o0qv5p"&&(ys.textContent=Hr),Oi=d(ft),Ie=f(ft,"DIV",{class:!0});var dt=Z(Ie);M(eo.$$.fragment,dt),Zi=d(dt),_s=f(dt,"P",{"data-svelte-h":!0}),F(_s)!=="svelte-1m8vqnl"&&(_s.innerHTML=Qr),Ui=d(dt),M(Et.$$.fragment,dt),Ii=d(dt),M(Pt.$$.fragment,dt),dt.forEach(l),ft.forEach(l),Fa=d(e),M(to.$$.fragment,e),xa=d(e),M(no.$$.fragment,e),Oa=d(e),ve=f(e,"DIV",{class:!0});var ct=Z(ve);M(oo.$$.fragment,ct),Ni=d(ct),Ms=f(ct,"P",{"data-svelte-h":!0}),F(Ms)!=="svelte-geirj3"&&(Ms.textContent=Yr),Wi=d(ct),ws=f(ct,"P",{"data-svelte-h":!0}),F(ws)!=="svelte-6rqfag"&&(ws.innerHTML=Dr),qi=d(ct),Ne=f(ct,"DIV",{class:!0});var pt=Z(Ne);M(so.$$.fragment,pt),Gi=d(pt),$s=f(pt,"P",{"data-svelte-h":!0}),F($s)!=="svelte-1vwprrf"&&($s.innerHTML=Ar),Xi=d(pt),M(Ht.$$.fragment,pt),zi=d(pt),M(Qt.$$.fragment,pt),pt.forEach(l),ct.forEach(l),Za=d(e),M(ao.$$.fragment,e),Ua=d(e),be=f(e,"DIV",{class:!0});var At=Z(be);M(lo.$$.fragment,At),Si=d(At),Ts=f(At,"P",{"data-svelte-h":!0}),F(Ts)!=="svelte-152z643"&&(Ts.textContent=Kr),Bi=d(At),ks=f(At,"P",{"data-svelte-h":!0}),F(ks)!=="svelte-6rqfag"&&(ks.innerHTML=ed),Ri=d(At),We=f(At,"DIV",{class:!0});var Kt=Z(We);M(io.$$.fragment,Kt),Li=d(Kt),Vs=f(Kt,"P",{"data-svelte-h":!0}),F(Vs)!=="svelte-118qms3"&&(Vs.innerHTML=td),Ei=d(Kt),M(Yt.$$.fragment,Kt),Pi=d(Kt),M(Dt.$$.fragment,Kt),Kt.forEach(l),At.forEach(l),Ia=d(e),M(ro.$$.fragment,e),Na=d(e),M(co.$$.fragment,e),Wa=d(e),Se=f(e,"DIV",{class:!0});var Gs=Z(Se);M(po.$$.fragment,Gs),Hi=d(Gs),Cs=f(Gs,"P",{"data-svelte-h":!0}),F(Cs)!=="svelte-fq54qp"&&(Cs.innerHTML=nd),Qi=d(Gs),Js=f(Gs,"DIV",{class:!0});var rd=Z(Js);M(mo.$$.fragment,rd),rd.forEach(l),Gs.forEach(l),qa=d(e),M(uo.$$.fragment,e),Ga=d(e),Be=f(e,"DIV",{class:!0});var Xs=Z(Be);M(go.$$.fragment,Xs),Yi=d(Xs),js=f(Xs,"P",{"data-svelte-h":!0}),F(js)!=="svelte-mqdlzq"&&(js.innerHTML=od),Di=d(Xs),Fs=f(Xs,"DIV",{class:!0});var dd=Z(Fs);M(fo.$$.fragment,dd),dd.forEach(l),Xs.forEach(l),Xa=d(e),M(ho.$$.fragment,e),za=d(e),Re=f(e,"DIV",{class:!0});var zs=Z(Re);M(vo.$$.fragment,zs),Ai=d(zs),xs=f(zs,"P",{"data-svelte-h":!0}),F(xs)!=="svelte-t0bmrx"&&(xs.innerHTML=sd),Ki=d(zs),Os=f(zs,"DIV",{class:!0});var cd=Z(Os);M(bo.$$.fragment,cd),cd.forEach(l),zs.forEach(l),Sa=d(e),M(yo.$$.fragment,e),Ba=d(e),M(_o.$$.fragment,e),Ra=d(e),Le=f(e,"DIV",{class:!0});var Ss=Z(Le);M(Mo.$$.fragment,Ss),er=d(Ss),Zs=f(Ss,"P",{"data-svelte-h":!0}),F(Zs)!=="svelte-1xco43c"&&(Zs.innerHTML=ad),tr=d(Ss),Us=f(Ss,"DIV",{class:!0});var pd=Z(Us);M(wo.$$.fragment,pd),pd.forEach(l),Ss.forEach(l),La=d(e),M($o.$$.fragment,e),Ea=d(e),Ee=f(e,"DIV",{class:!0});var Bs=Z(Ee);M(To.$$.fragment,Bs),nr=d(Bs),Is=f(Bs,"P",{"data-svelte-h":!0}),F(Is)!=="svelte-1u70qsc"&&(Is.innerHTML=ld),or=d(Bs),Ns=f(Bs,"DIV",{class:!0});var md=Z(Ns);M(ko.$$.fragment,md),md.forEach(l),Bs.forEach(l),Pa=d(e),M(Vo.$$.fragment,e),Ha=d(e),M(Co.$$.fragment,e),Qa=d(e),Pe=f(e,"DIV",{class:!0});var Rs=Z(Pe);M(Jo.$$.fragment,Rs),sr=d(Rs),Ws=f(Rs,"P",{"data-svelte-h":!0}),F(Ws)!=="svelte-ign31x"&&(Ws.innerHTML=id),ar=d(Rs),qs=f(Rs,"DIV",{class:!0});var ud=Z(qs);M(jo.$$.fragment,ud),ud.forEach(l),Rs.forEach(l),Ya=d(e),Ls=f(e,"P",{}),Z(Ls).forEach(l),this.h()},h(){C(t,"name","hf:doc:metadata"),C(t,"content",zc),C(z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(B,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(v,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Io,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(No,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(ne,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Ce,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(pe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(ie,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(qe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Je,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(me,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(je,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(ue,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Fe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(ge,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(xe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(fe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Oe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(oe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Ze,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(se,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Ue,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(ae,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(re,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Ge,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(de,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(he,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(ce,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Xe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Ie,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(ze,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Ne,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(ve,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(We,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(be,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Js,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Se,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Fs,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Be,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Os,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Re,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Us,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Le,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Ns,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Ee,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(qs,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Pe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(e,u){i(document.head,t),h(e,a,u),h(e,o,u),h(e,s,u),w(m,e,u),h(e,n,u),w(c,e,u),h(e,x,u),w(J,e,u),h(e,j,u),h(e,v,u),w(k,v,null),i(v,V),i(v,T),i(v,W),i(v,z),w(S,z,null),i(z,ee),i(z,te),i(v,E),i(v,B),w(X,B,null),i(B,R),i(B,L),h(e,N,u),w(U,e,u),h(e,H,u),h(e,A,u),h(e,Oo,u),w(an,e,u),h(e,Ds,u),h(e,ne,u),w(ln,ne,null),i(ne,al),i(ne,Zo),i(ne,ll),i(ne,Uo),i(ne,il),i(ne,Io),w(rn,Io,null),i(ne,rl),i(ne,No),w(dn,No,null),h(e,As,u),w(cn,e,u),h(e,Ks,u),h(e,pe,u),w(pn,pe,null),i(pe,dl),i(pe,Wo),i(pe,cl),i(pe,qo),i(pe,pl),i(pe,Ce),w(mn,Ce,null),i(Ce,ml),i(Ce,Go),i(Ce,ul),w(bt,Ce,null),i(Ce,gl),w(yt,Ce,null),h(e,ea,u),w(un,e,u),h(e,ta,u),h(e,qe,u),w(gn,qe,null),i(qe,fl),i(qe,Xo),i(qe,hl),i(qe,ie),w(fn,ie,null),i(ie,vl),i(ie,zo),i(ie,bl),w(_t,ie,null),i(ie,yl),w(Mt,ie,null),i(ie,_l),w(wt,ie,null),h(e,na,u),w(hn,e,u),h(e,oa,u),h(e,me,u),w(vn,me,null),i(me,Ml),i(me,So),i(me,wl),i(me,Bo),i(me,$l),i(me,Je),w(bn,Je,null),i(Je,Tl),i(Je,Ro),i(Je,kl),w($t,Je,null),i(Je,Vl),w(Tt,Je,null),h(e,sa,u),w(yn,e,u),h(e,aa,u),h(e,ue,u),w(_n,ue,null),i(ue,Cl),i(ue,Lo),i(ue,Jl),i(ue,Eo),i(ue,jl),i(ue,je),w(Mn,je,null),i(je,Fl),i(je,Po),i(je,xl),w(kt,je,null),i(je,Ol),w(Vt,je,null),h(e,la,u),w(wn,e,u),h(e,ia,u),h(e,ge,u),w($n,ge,null),i(ge,Zl),i(ge,Ho),i(ge,Ul),i(ge,Qo),i(ge,Il),i(ge,Fe),w(Tn,Fe,null),i(Fe,Nl),i(Fe,Yo),i(Fe,Wl),w(Ct,Fe,null),i(Fe,ql),w(Jt,Fe,null),h(e,ra,u),w(kn,e,u),h(e,da,u),h(e,Vn,u),h(e,ca,u),w(Cn,e,u),h(e,pa,u),h(e,fe,u),w(Jn,fe,null),i(fe,Gl),i(fe,Do),i(fe,Xl),i(fe,Ao),i(fe,zl),i(fe,xe),w(jn,xe,null),i(xe,Sl),i(xe,Ko),i(xe,Bl),w(jt,xe,null),i(xe,Rl),w(Ft,xe,null),h(e,ma,u),w(Fn,e,u),h(e,ua,u),h(e,oe,u),w(xn,oe,null),i(oe,Ll),i(oe,es),i(oe,El),i(oe,ts),i(oe,Pl),i(oe,ns),i(oe,Hl),i(oe,Oe),w(On,Oe,null),i(Oe,Ql),i(Oe,os),i(Oe,Yl),w(xt,Oe,null),i(Oe,Dl),w(Ot,Oe,null),h(e,ga,u),w(Zn,e,u),h(e,fa,u),h(e,se,u),w(Un,se,null),i(se,Al),i(se,ss),i(se,Kl),i(se,as),i(se,ei),i(se,ls),i(se,ti),i(se,Ze),w(In,Ze,null),i(Ze,ni),i(Ze,is),i(Ze,oi),w(Zt,Ze,null),i(Ze,si),w(Ut,Ze,null),h(e,ha,u),w(Nn,e,u),h(e,va,u),h(e,ae,u),w(Wn,ae,null),i(ae,ai),i(ae,rs),i(ae,li),i(ae,ds),i(ae,ii),i(ae,cs),i(ae,ri),i(ae,Ue),w(qn,Ue,null),i(Ue,di),i(Ue,ps),i(Ue,ci),w(It,Ue,null),i(Ue,pi),w(Nt,Ue,null),h(e,ba,u),w(Gn,e,u),h(e,ya,u),h(e,Ge,u),w(Xn,Ge,null),i(Ge,mi),i(Ge,ms),i(Ge,ui),i(Ge,re),w(zn,re,null),i(re,gi),i(re,us),i(re,fi),w(Wt,re,null),i(re,hi),w(qt,re,null),i(re,vi),w(Gt,re,null),h(e,_a,u),w(Sn,e,u),h(e,Ma,u),h(e,Bn,u),h(e,wa,u),w(Rn,e,u),h(e,$a,u),h(e,he,u),w(Ln,he,null),i(he,bi),i(he,gs),i(he,yi),i(he,fs),i(he,_i),i(he,de),w(En,de,null),i(de,Mi),i(de,hs),i(de,wi),w(Xt,de,null),i(de,$i),w(zt,de,null),i(de,Ti),w(St,de,null),h(e,Ta,u),w(Pn,e,u),h(e,ka,u),h(e,Hn,u),h(e,Va,u),w(Qn,e,u),h(e,Ca,u),h(e,Xe,u),w(Yn,Xe,null),i(Xe,ki),i(Xe,vs),i(Xe,Vi),i(Xe,ce),w(Dn,ce,null),i(ce,Ci),i(ce,bs),i(ce,Ji),w(Bt,ce,null),i(ce,ji),w(Rt,ce,null),i(ce,Fi),w(Lt,ce,null),h(e,Ja,u),w(An,e,u),h(e,ja,u),h(e,ze,u),w(Kn,ze,null),i(ze,xi),i(ze,ys),i(ze,Oi),i(ze,Ie),w(eo,Ie,null),i(Ie,Zi),i(Ie,_s),i(Ie,Ui),w(Et,Ie,null),i(Ie,Ii),w(Pt,Ie,null),h(e,Fa,u),w(to,e,u),h(e,xa,u),w(no,e,u),h(e,Oa,u),h(e,ve,u),w(oo,ve,null),i(ve,Ni),i(ve,Ms),i(ve,Wi),i(ve,ws),i(ve,qi),i(ve,Ne),w(so,Ne,null),i(Ne,Gi),i(Ne,$s),i(Ne,Xi),w(Ht,Ne,null),i(Ne,zi),w(Qt,Ne,null),h(e,Za,u),w(ao,e,u),h(e,Ua,u),h(e,be,u),w(lo,be,null),i(be,Si),i(be,Ts),i(be,Bi),i(be,ks),i(be,Ri),i(be,We),w(io,We,null),i(We,Li),i(We,Vs),i(We,Ei),w(Yt,We,null),i(We,Pi),w(Dt,We,null),h(e,Ia,u),w(ro,e,u),h(e,Na,u),w(co,e,u),h(e,Wa,u),h(e,Se,u),w(po,Se,null),i(Se,Hi),i(Se,Cs),i(Se,Qi),i(Se,Js),w(mo,Js,null),h(e,qa,u),w(uo,e,u),h(e,Ga,u),h(e,Be,u),w(go,Be,null),i(Be,Yi),i(Be,js),i(Be,Di),i(Be,Fs),w(fo,Fs,null),h(e,Xa,u),w(ho,e,u),h(e,za,u),h(e,Re,u),w(vo,Re,null),i(Re,Ai),i(Re,xs),i(Re,Ki),i(Re,Os),w(bo,Os,null),h(e,Sa,u),w(yo,e,u),h(e,Ba,u),w(_o,e,u),h(e,Ra,u),h(e,Le,u),w(Mo,Le,null),i(Le,er),i(Le,Zs),i(Le,tr),i(Le,Us),w(wo,Us,null),h(e,La,u),w($o,e,u),h(e,Ea,u),h(e,Ee,u),w(To,Ee,null),i(Ee,nr),i(Ee,Is),i(Ee,or),i(Ee,Ns),w(ko,Ns,null),h(e,Pa,u),w(Vo,e,u),h(e,Ha,u),w(Co,e,u),h(e,Qa,u),h(e,Pe,u),w(Jo,Pe,null),i(Pe,sr),i(Pe,Ws),i(Pe,ar),i(Pe,qs),w(jo,qs,null),h(e,Ya,u),h(e,Ls,u),Da=!0},p(e,[u]){const He={};u&2&&(He.$$scope={dirty:u,ctx:e}),bt.$set(He);const Fo={};u&2&&(Fo.$$scope={dirty:u,ctx:e}),yt.$set(Fo);const xo={};u&2&&(xo.$$scope={dirty:u,ctx:e}),_t.$set(xo);const ye={};u&2&&(ye.$$scope={dirty:u,ctx:e}),Mt.$set(ye);const Es={};u&2&&(Es.$$scope={dirty:u,ctx:e}),wt.$set(Es);const Ps={};u&2&&(Ps.$$scope={dirty:u,ctx:e}),$t.$set(Ps);const Qe={};u&2&&(Qe.$$scope={dirty:u,ctx:e}),Tt.$set(Qe);const Ye={};u&2&&(Ye.$$scope={dirty:u,ctx:e}),kt.$set(Ye);const mt={};u&2&&(mt.$$scope={dirty:u,ctx:e}),Vt.$set(mt);const _e={};u&2&&(_e.$$scope={dirty:u,ctx:e}),Ct.$set(_e);const De={};u&2&&(De.$$scope={dirty:u,ctx:e}),Jt.$set(De);const Ae={};u&2&&(Ae.$$scope={dirty:u,ctx:e}),jt.$set(Ae);const Ke={};u&2&&(Ke.$$scope={dirty:u,ctx:e}),Ft.$set(Ke);const et={};u&2&&(et.$$scope={dirty:u,ctx:e}),xt.$set(et);const tt={};u&2&&(tt.$$scope={dirty:u,ctx:e}),Ot.$set(tt);const nt={};u&2&&(nt.$$scope={dirty:u,ctx:e}),Zt.$set(nt);const ot={};u&2&&(ot.$$scope={dirty:u,ctx:e}),Ut.$set(ot);const st={};u&2&&(st.$$scope={dirty:u,ctx:e}),It.$set(st);const Me={};u&2&&(Me.$$scope={dirty:u,ctx:e}),Nt.$set(Me);const at={};u&2&&(at.$$scope={dirty:u,ctx:e}),Wt.$set(at);const we={};u&2&&(we.$$scope={dirty:u,ctx:e}),qt.$set(we);const lt={};u&2&&(lt.$$scope={dirty:u,ctx:e}),Gt.$set(lt);const $e={};u&2&&($e.$$scope={dirty:u,ctx:e}),Xt.$set($e);const it={};u&2&&(it.$$scope={dirty:u,ctx:e}),zt.$set(it);const ut={};u&2&&(ut.$$scope={dirty:u,ctx:e}),St.$set(ut);const Te={};u&2&&(Te.$$scope={dirty:u,ctx:e}),Bt.$set(Te);const rt={};u&2&&(rt.$$scope={dirty:u,ctx:e}),Rt.$set(rt);const ke={};u&2&&(ke.$$scope={dirty:u,ctx:e}),Lt.$set(ke);const gt={};u&2&&(gt.$$scope={dirty:u,ctx:e}),Et.$set(gt);const Ve={};u&2&&(Ve.$$scope={dirty:u,ctx:e}),Pt.$set(Ve);const ft={};u&2&&(ft.$$scope={dirty:u,ctx:e}),Ht.$set(ft);const dt={};u&2&&(dt.$$scope={dirty:u,ctx:e}),Qt.$set(dt);const ct={};u&2&&(ct.$$scope={dirty:u,ctx:e}),Yt.$set(ct);const pt={};u&2&&(pt.$$scope={dirty:u,ctx:e}),Dt.$set(pt)},i(e){Da\|\|(b(m.$$.fragment,e),b(c.$$.fragment,e),b(J.$$.fragment,e),b(k.$$.fragment,e),b(S.$$.fragment,e),b(X.$$.fragment,e),b(U.$$.fragment,e),b(an.$$.fragment,e),b(ln.$$.fragment,e),b(rn.$$.fragment,e),b(dn.$$.fragment,e),b(cn.$$.fragment,e),b(pn.$$.fragment,e),b(mn.$$.fragment,e),b(bt.$$.fragment,e),b(yt.$$.fragment,e),b(un.$$.fragment,e),b(gn.$$.fragment,e),b(fn.$$.fragment,e),b(_t.$$.fragment,e),b(Mt.$$.fragment,e),b(wt.$$.fragment,e),b(hn.$$.fragment,e),b(vn.$$.fragment,e),b(bn.$$.fragment,e),b($t.$$.fragment,e),b(Tt.$$.fragment,e),b(yn.$$.fragment,e),b(_n.$$.fragment,e),b(Mn.$$.fragment,e),b(kt.$$.fragment,e),b(Vt.$$.fragment,e),b(wn.$$.fragment,e),b($n.$$.fragment,e),b(Tn.$$.fragment,e),b(Ct.$$.fragment,e),b(Jt.$$.fragment,e),b(kn.$$.fragment,e),b(Cn.$$.fragment,e),b(Jn.$$.fragment,e),b(jn.$$.fragment,e),b(jt.$$.fragment,e),b(Ft.$$.fragment,e),b(Fn.$$.fragment,e),b(xn.$$.fragment,e),b(On.$$.fragment,e),b(xt.$$.fragment,e),b(Ot.$$.fragment,e),b(Zn.$$.fragment,e),b(Un.$$.fragment,e),b(In.$$.fragment,e),b(Zt.$$.fragment,e),b(Ut.$$.fragment,e),b(Nn.$$.fragment,e),b(Wn.$$.fragment,e),b(qn.$$.fragment,e),b(It.$$.fragment,e),b(Nt.$$.fragment,e),b(Gn.$$.fragment,e),b(Xn.$$.fragment,e),b(zn.$$.fragment,e),b(Wt.$$.fragment,e),b(qt.$$.fragment,e),b(Gt.$$.fragment,e),b(Sn.$$.fragment,e),b(Rn.$$.fragment,e),b(Ln.$$.fragment,e),b(En.$$.fragment,e),b(Xt.$$.fragment,e),b(zt.$$.fragment,e),b(St.$$.fragment,e),b(Pn.$$.fragment,e),b(Qn.$$.fragment,e),b(Yn.$$.fragment,e),b(Dn.$$.fragment,e),b(Bt.$$.fragment,e),b(Rt.$$.fragment,e),b(Lt.$$.fragment,e),b(An.$$.fragment,e),b(Kn.$$.fragment,e),b(eo.$$.fragment,e),b(Et.$$.fragment,e),b(Pt.$$.fragment,e),b(to.$$.fragment,e),b(no.$$.fragment,e),b(oo.$$.fragment,e),b(so.$$.fragment,e),b(Ht.$$.fragment,e),b(Qt.$$.fragment,e),b(ao.$$.fragment,e),b(lo.$$.fragment,e),b(io.$$.fragment,e),b(Yt.$$.fragment,e),b(Dt.$$.fragment,e),b(ro.$$.fragment,e),b(co.$$.fragment,e),b(po.$$.fragment,e),b(mo.$$.fragment,e),b(uo.$$.fragment,e),b(go.$$.fragment,e),b(fo.$$.fragment,e),b(ho.$$.fragment,e),b(vo.$$.fragment,e),b(bo.$$.fragment,e),b(yo.$$.fragment,e),b(_o.$$.fragment,e),b(Mo.$$.fragment,e),b(wo.$$.fragment,e),b($o.$$.fragment,e),b(To.$$.fragment,e),b(ko.$$.fragment,e),b(Vo.$$.fragment,e),b(Co.$$.fragment,e),b(Jo.$$.fragment,e),b(jo.$$.fragment,e),Da=!0)},o(e){y(m.$$.fragment,e),y(c.$$.fragment,e),y(J.$$.fragment,e),y(k.$$.fragment,e),y(S.$$.fragment,e),y(X.$$.fragment,e),y(U.$$.fragment,e),y(an.$$.fragment,e),y(ln.$$.fragment,e),y(rn.$$.fragment,e),y(dn.$$.fragment,e),y(cn.$$.fragment,e),y(pn.$$.fragment,e),y(mn.$$.fragment,e),y(bt.$$.fragment,e),y(yt.$$.fragment,e),y(un.$$.fragment,e),y(gn.$$.fragment,e),y(fn.$$.fragment,e),y(_t.$$.fragment,e),y(Mt.$$.fragment,e),y(wt.$$.fragment,e),y(hn.$$.fragment,e),y(vn.$$.fragment,e),y(bn.$$.fragment,e),y($t.$$.fragment,e),y(Tt.$$.fragment,e),y(yn.$$.fragment,e),y(_n.$$.fragment,e),y(Mn.$$.fragment,e),y(kt.$$.fragment,e),y(Vt.$$.fragment,e),y(wn.$$.fragment,e),y($n.$$.fragment,e),y(Tn.$$.fragment,e),y(Ct.$$.fragment,e),y(Jt.$$.fragment,e),y(kn.$$.fragment,e),y(Cn.$$.fragment,e),y(Jn.$$.fragment,e),y(jn.$$.fragment,e),y(jt.$$.fragment,e),y(Ft.$$.fragment,e),y(Fn.$$.fragment,e),y(xn.$$.fragment,e),y(On.$$.fragment,e),y(xt.$$.fragment,e),y(Ot.$$.fragment,e),y(Zn.$$.fragment,e),y(Un.$$.fragment,e),y(In.$$.fragment,e),y(Zt.$$.fragment,e),y(Ut.$$.fragment,e),y(Nn.$$.fragment,e),y(Wn.$$.fragment,e),y(qn.$$.fragment,e),y(It.$$.fragment,e),y(Nt.$$.fragment,e),y(Gn.$$.fragment,e),y(Xn.$$.fragment,e),y(zn.$$.fragment,e),y(Wt.$$.fragment,e),y(qt.$$.fragment,e),y(Gt.$$.fragment,e),y(Sn.$$.fragment,e),y(Rn.$$.fragment,e),y(Ln.$$.fragment,e),y(En.$$.fragment,e),y(Xt.$$.fragment,e),y(zt.$$.fragment,e),y(St.$$.fragment,e),y(Pn.$$.fragment,e),y(Qn.$$.fragment,e),y(Yn.$$.fragment,e),y(Dn.$$.fragment,e),y(Bt.$$.fragment,e),y(Rt.$$.fragment,e),y(Lt.$$.fragment,e),y(An.$$.fragment,e),y(Kn.$$.fragment,e),y(eo.$$.fragment,e),y(Et.$$.fragment,e),y(Pt.$$.fragment,e),y(to.$$.fragment,e),y(no.$$.fragment,e),y(oo.$$.fragment,e),y(so.$$.fragment,e),y(Ht.$$.fragment,e),y(Qt.$$.fragment,e),y(ao.$$.fragment,e),y(lo.$$.fragment,e),y(io.$$.fragment,e),y(Yt.$$.fragment,e),y(Dt.$$.fragment,e),y(ro.$$.fragment,e),y(co.$$.fragment,e),y(po.$$.fragment,e),y(mo.$$.fragment,e),y(uo.$$.fragment,e),y(go.$$.fragment,e),y(fo.$$.fragment,e),y(ho.$$.fragment,e),y(vo.$$.fragment,e),y(bo.$$.fragment,e),y(yo.$$.fragment,e),y(_o.$$.fragment,e),y(Mo.$$.fragment,e),y(wo.$$.fragment,e),y($o.$$.fragment,e),y(To.$$.fragment,e),y(ko.$$.fragment,e),y(Vo.$$.fragment,e),y(Co.$$.fragment,e),y(Jo.$$.fragment,e),y(jo.$$.fragment,e),Da=!1},d(e){e&&(l(a),l(o),l(s),l(n),l(x),l(j),l(v),l(N),l(H),l(A),l(Oo),l(Ds),l(ne),l(As),l(Ks),l(pe),l(ea),l(ta),l(qe),l(na),l(oa),l(me),l(sa),l(aa),l(ue),l(la),l(ia),l(ge),l(ra),l(da),l(Vn),l(ca),l(pa),l(fe),l(ma),l(ua),l(oe),l(ga),l(fa),l(se),l(ha),l(va),l(ae),l(ba),l(ya),l(Ge),l(_a),l(Ma),l(Bn),l(wa),l($a),l(he),l(Ta),l(ka),l(Hn),l(Va),l(Ca),l(Xe),l(Ja),l(ja),l(ze),l(Fa),l(xa),l(Oa),l(ve),l(Za),l(Ua),l(be),l(Ia),l(Na),l(Wa),l(Se),l(qa),l(Ga),l(Be),l(Xa),l(za),l(Re),l(Sa),l(Ba),l(Ra),l(Le),l(La),l(Ea),l(Ee),l(Pa),l(Ha),l(Qa),l(Pe),l(Ya),l(Ls)),l(t),$(m,e),$(c,e),$(J,e),$(k),$(S),$(X),$(U,e),$(an,e),$(ln),$(rn),$(dn),$(cn,e),$(pn),$(mn),$(bt),$(yt),$(un,e),$(gn),$(fn),$(_t),$(Mt),$(wt),$(hn,e),$(vn),$(bn),$($t),$(Tt),$(yn,e),$(_n),$(Mn),$(kt),$(Vt),$(wn,e),$($n),$(Tn),$(Ct),$(Jt),$(kn,e),$(Cn,e),$(Jn),$(jn),$(jt),$(Ft),$(Fn,e),$(xn),$(On),$(xt),$(Ot),$(Zn,e),$(Un),$(In),$(Zt),$(Ut),$(Nn,e),$(Wn),$(qn),$(It),$(Nt),$(Gn,e),$(Xn),$(zn),$(Wt),$(qt),$(Gt),$(Sn,e),$(Rn,e),$(Ln),$(En),$(Xt),$(zt),$(St),$(Pn,e),$(Qn,e),$(Yn),$(Dn),$(Bt),$(Rt),$(Lt),$(An,e),$(Kn),$(eo),$(Et),$(Pt),$(to,e),$(no,e),$(oo),$(so),$(Ht),$(Qt),$(ao,e),$(lo),$(io),$(Yt),$(Dt),$(ro,e),$(co,e),$(po),$(mo),$(uo,e),$(go),$(fo),$(ho,e),$(vo),$(bo),$(yo,e),$(_o,e),$(Mo),$(wo),$($o,e),$(To),$(ko),$(Vo,e),$(Co,e),$(Jo),$(jo)}}}const zc='{"title":"Models","local":"models","sections":[{"title":"Generic model classes","local":"optimum.intel.openvino.modeling_base.OVBaseModel","sections":[],"depth":2},{"title":"Natural Language Processing","local":"natural-language-processing","sections":[{"title":"OVModelForCausalLM","local":"optimum.intel.OVModelForCausalLM","sections":[],"depth":3},{"title":"OVModelForMaskedLM","local":"optimum.intel.OVModelForMaskedLM","sections":[],"depth":3},{"title":"OVModelForSeq2SeqLM","local":"optimum.intel.OVModelForSeq2SeqLM","sections":[],"depth":3},{"title":"OVModelForQuestionAnswering","local":"optimum.intel.OVModelForQuestionAnswering","sections":[],"depth":3},{"title":"OVModelForSequenceClassification","local":"optimum.intel.OVModelForSequenceClassification","sections":[],"depth":3},{"title":"OVModelForTokenClassification","local":"optimum.intel.OVModelForTokenClassification","sections":[],"depth":3}],"depth":2},{"title":"Audio","local":"audio","sections":[{"title":"OVModelForAudioClassification","local":"optimum.intel.OVModelForAudioClassification","sections":[],"depth":3},{"title":"OVModelForAudioFrameClassification","local":"optimum.intel.OVModelForAudioFrameClassification","sections":[],"depth":3},{"title":"OVModelForCTC","local":"optimum.intel.OVModelForCTC","sections":[],"depth":3},{"title":"OVModelForAudioXVector","local":"optimum.intel.OVModelForAudioXVector","sections":[],"depth":3},{"title":"OVModelForSpeechSeq2Seq","local":"optimum.intel.OVModelForSpeechSeq2Seq","sections":[],"depth":3}],"depth":2},{"title":"Computer Vision","local":"computer-vision","sections":[{"title":"OVModelForImageClassification","local":"optimum.intel.OVModelForImageClassification","sections":[],"depth":3}],"depth":2},{"title":"Multimodal","local":"multimodal","sections":[{"title":"OVModelForVision2Seq","local":"optimum.intel.OVModelForVision2Seq","sections":[],"depth":3},{"title":"OVModelForPix2Struct","local":"optimum.intel.OVModelForPix2Struct","sections":[],"depth":3}],"depth":2},{"title":"Custom Tasks","local":"custom-tasks","sections":[{"title":"OVModelForCustomTasks","local":"optimum.intel.OVModelForCustomTasks","sections":[],"depth":3},{"title":"OVModelForFeatureExtraction","local":"optimum.intel.OVModelForFeatureExtraction","sections":[],"depth":3}],"depth":2},{"title":"Text-to-image","local":"text-to-image","sections":[{"title":"OVStableDiffusionPipeline","local":"optimum.intel.OVStableDiffusionPipeline","sections":[],"depth":3},{"title":"OVStableDiffusionXLPipeline","local":"optimum.intel.OVStableDiffusionXLPipeline","sections":[],"depth":3},{"title":"OVLatentConsistencyModelPipeline","local":"optimum.intel.OVLatentConsistencyModelPipeline","sections":[],"depth":3}],"depth":2},{"title":"Image-to-image","local":"image-to-image","sections":[{"title":"OVStableDiffusionImg2ImgPipeline","local":"optimum.intel.OVStableDiffusionImg2ImgPipeline","sections":[],"depth":3},{"title":"OVStableDiffusionXLImg2ImgPipeline","local":"optimum.intel.OVStableDiffusionXLImg2ImgPipeline","sections":[],"depth":3}],"depth":2},{"title":"Inpainting","local":"inpainting","sections":[{"title":"OVStableDiffusionInpaintPipeline","local":"optimum.intel.OVStableDiffusionInpaintPipeline","sections":[],"depth":3}],"depth":2}],"depth":1}';function Sc(p){return lr(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Qc extends tl{constructor(t){super(),nl(this,t,Sc,Xc,el,{})}}export{Qc as component};

Xet Storage Details

Size:: 232 kB
Xet hash:: dc55423579ad0e442dd87b083bf128f3a5c3ce143d1f3bd1efbb14fe0042203f

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.