Buckets:

rtrm's picture
download
raw
13.5 kB
import{s as it,h as De,n as at,o as gt}from"../chunks/scheduler.8b74b908.js";import{S as st,i as ut,g as a,s as n,r as u,A as rt,h as g,f as o,c as i,j as X,u as r,x as s,k as Z,y as pt,a as l,v as p,d as c,t as m,w as d}from"../chunks/index.0ed2a570.js";import{H as x,E as ct}from"../chunks/EditOnGithub.d2d81eda.js";function mt(Ve){let y,ee,N,te,C,oe,v,Oe='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/google-cloud/thumbnail.png" alt="Hugging Face x Google Cloud"/>',le,w,Ke="Hugging Face collaborates with Google across open science, open source, cloud, and hardware to enable companies to build their own AI with the latest open models from Hugging Face and the latest cloud and hardware features from Google Cloud.",ne,H,Se="Hugging Face enables new experiences for Google Cloud customers. They can easily train and deploy Hugging Face models on Google Kubernetes Engine (GKE), Vertex AI, and Cloud Run, on any hardware available in Google Cloud using Hugging Face Deep Learning Containers (DLCs) or our no-code integrations.",ie,G,ae,b,ge,_,Re="For advanced scenarios, you can pull any Hugging Face DLCs from the Google Cloud Artifact Registry directly in your environment. We curated a list of notebook examples on how to deploy models with Hugging Face DLCs in:",se,T,Be='<li><a href="https://github.com/huggingface/Google-Cloud-Containers/tree/main/examples/vertex-ai#inference-examples" rel="nofollow">Vertex AI</a></li> <li><a href="https://github.com/huggingface/Google-Cloud-Containers/tree/main/examples/gke#inference-examples" rel="nofollow">GKE</a></li> <li><a href="https://github.com/huggingface/Google-Cloud-Containers/tree/main/examples/cloud-run#inference-examples" rel="nofollow">Cloud Run</a> (preview)</li>',ue,F,re,L,pe,E,We="If you want to deploy a model from the Hub in your Google Cloud account on Vertex AI or GKE, you can use our no-code integrations. Below, you will find step-by-step instructions on how to deploy (Gemma 2 9B)[https://huggingface.co/google/gemma-2-9b-it]:",ce,I,qe='<li>On the model page, open the “Deploy” menu, and select “Google Cloud”. This will bring you straight into the Google Cloud Console.</li> <li>Select Vertex AI or GKE as a deployment option.</li> <li>Paste a <a href="https://huggingface.co/docs/hub/en/security-tokens" rel="nofollow">Hugging Face Token</a> with “Read access contents of all public gated repos you can access” permission.</li> <li>If Vertex AI is selected, click on “Deploy”. If GKE is selected, paste the manifest code and apply to your EKS cluster.</li>',me,M,Ue="Alternatively, you can follow this short video.",de,f,je,fe,A,he,P,ze='You can deploy a model from the Hub on Hugging Face <a href="https://huggingface.co/inference-endpoints/dedicated" rel="nofollow">Inference Endpoints</a> on Google Cloud instances managed by Hugging Face. Below, you will find step-by-step instructions on how to deploy <a href="https://huggingface.co/google/gemma-2-9b-it" rel="nofollow">Gemma 2 9B</a>:',$e,k,Ye="<li>On the model page, open the “Deploy” menu, and select “Inference Endpoints (dedicated)”. This will now bring you in the Inference Endpoint deployment page.</li> <li>Select Google Cloud Platform, scroll down and click on “Create Endpoint”.</li>",xe,D,Je="Alternatively, you can follow this short video.",ye,h,Ne,Ce,V,ve,O,we,K,Qe='You can deploy a Hugging Face model from the Vertex AI Model Garden on Vertex AI or GKE. Below, you will find step-by-step instructions on how to deploy <a href="https://huggingface.co/google/gemma-2-9b-it" rel="nofollow">Gemma 2 9B</a>:',He,S,Xe='<li>On <a href="https://console.cloud.google.com/vertex-ai/model-garden" rel="nofollow">Vertex AI Model Garden landing page</a>, you can browse Hugging Face models by clicking “Deploy From Hugging Face” at the top left, or scroll down to see our curated list of open source models as well as the full catalog by clicking on “Hugging Face” in the Featured Partner section.</li> <li>Once you found the model that you want to deploy, you can select Vertex AI or GKE as a deployment option.</li> <li>Paste a <a href="https://huggingface.co/docs/hub/en/security-tokens" rel="nofollow">Hugging Face Token</a> with “Read access contents of all public gated repos you can access” permission.</li> <li>If Vertex AI is selected, click on “Deploy”. If GKE is selected, paste the manifest code and apply to your EKS cluster.</li>',Ge,R,Ze="Alternatively, you can follow this short video.",be,$,et,_e,B,Te,W,Fe,q,tt="For advanced scenarios, you can pull the containers from the Google Cloud Artifact Registry directly in your environment. We curated a list of notebook examples on how to train models with Hugging Face DLCs in:",Le,U,ot="<li>(Vertex AI)[https://github.com/huggingface/Google-Cloud-Containers/tree/main/examples/vertex-ai#training-examples]</li> <li>(GKE)[https://github.com/huggingface/Google-Cloud-Containers/tree/main/examples/gke#training-examples]</li>",Ee,j,Ie,z,lt='If you have any issues using Hugging Face on Google Cloud, you can get community support by creating a new topic in the <a href="https://discuss.huggingface.co/c/google-cloud/69/l/latest" rel="nofollow">Forum</a> dedicated to Google Cloud usage.',Me,Y,nt='Hugging Face DLCs are open source and licensed under Apache 2.0 within the <a href="https://github.com/huggingface/Google-Cloud-Containers" rel="nofollow">Google-Cloud-Containers</a> repository. For premium support, our <a href="https://huggingface.co/support" rel="nofollow">Expert Support Program</a> gives you direct dedicated support from our team.',Ae,J,Pe,Q,ke;return C=new x({props:{title:"Hugging Face on Google Cloud",local:"hugging-face-on-google-cloud",headingTag:"h1"}}),G=new x({props:{title:"Deploy Models on Google Cloud",local:"deploy-models-on-google-cloud",headingTag:"h2"}}),b=new x({props:{title:"With Hugging Face DLCs",local:"with-hugging-face-dlcs",headingTag:"h3"}}),F=new x({props:{title:"From the Hub Model Page",local:"from-the-hub-model-page",headingTag:"h3"}}),L=new x({props:{title:"On Vertex AI or GKE",local:"on-vertex-ai-or-gke",headingTag:"h4"}}),A=new x({props:{title:"On Hugging Face Inference Endpoints",local:"on-hugging-face-inference-endpoints",headingTag:"h4"}}),V=new x({props:{title:"From Vertex AI Model Garden",local:"from-vertex-ai-model-garden",headingTag:"h3"}}),O=new x({props:{title:"On Vertex AI or GKE",local:"on-vertex-ai-or-gke",headingTag:"h4"}}),B=new x({props:{title:"Train models on Google Cloud",local:"train-models-on-google-cloud",headingTag:"h2"}}),W=new x({props:{title:"With Hugging Face DLCs",local:"with-hugging-face-dlcs",headingTag:"h3"}}),j=new x({props:{title:"Support",local:"support",headingTag:"h2"}}),J=new ct({props:{source:"https://github.com/huggingface/Google-Cloud-Containers/blob/main/docs/source/index.mdx"}}),{c(){y=a("meta"),ee=n(),N=a("p"),te=n(),u(C.$$.fragment),oe=n(),v=a("p"),v.innerHTML=Oe,le=n(),w=a("p"),w.textContent=Ke,ne=n(),H=a("p"),H.textContent=Se,ie=n(),u(G.$$.fragment),ae=n(),u(b.$$.fragment),ge=n(),_=a("p"),_.textContent=Re,se=n(),T=a("ul"),T.innerHTML=Be,ue=n(),u(F.$$.fragment),re=n(),u(L.$$.fragment),pe=n(),E=a("p"),E.textContent=We,ce=n(),I=a("ol"),I.innerHTML=qe,me=n(),M=a("p"),M.textContent=Ue,de=n(),f=a("video"),fe=n(),u(A.$$.fragment),he=n(),P=a("p"),P.innerHTML=ze,$e=n(),k=a("ol"),k.innerHTML=Ye,xe=n(),D=a("p"),D.textContent=Je,ye=n(),h=a("video"),Ce=n(),u(V.$$.fragment),ve=n(),u(O.$$.fragment),we=n(),K=a("p"),K.innerHTML=Qe,He=n(),S=a("ol"),S.innerHTML=Xe,Ge=n(),R=a("p"),R.textContent=Ze,be=n(),$=a("video"),_e=n(),u(B.$$.fragment),Te=n(),u(W.$$.fragment),Fe=n(),q=a("p"),q.textContent=tt,Le=n(),U=a("ul"),U.innerHTML=ot,Ee=n(),u(j.$$.fragment),Ie=n(),z=a("p"),z.innerHTML=lt,Me=n(),Y=a("p"),Y.innerHTML=nt,Ae=n(),u(J.$$.fragment),Pe=n(),Q=a("p"),this.h()},l(e){const t=rt("svelte-u9bgzb",document.head);y=g(t,"META",{name:!0,content:!0}),t.forEach(o),ee=i(e),N=g(e,"P",{}),X(N).forEach(o),te=i(e),r(C.$$.fragment,e),oe=i(e),v=g(e,"P",{"data-svelte-h":!0}),s(v)!=="svelte-5bmp1t"&&(v.innerHTML=Oe),le=i(e),w=g(e,"P",{"data-svelte-h":!0}),s(w)!=="svelte-1xc3l3u"&&(w.textContent=Ke),ne=i(e),H=g(e,"P",{"data-svelte-h":!0}),s(H)!=="svelte-1pwu5f6"&&(H.textContent=Se),ie=i(e),r(G.$$.fragment,e),ae=i(e),r(b.$$.fragment,e),ge=i(e),_=g(e,"P",{"data-svelte-h":!0}),s(_)!=="svelte-1ybod0l"&&(_.textContent=Re),se=i(e),T=g(e,"UL",{"data-svelte-h":!0}),s(T)!=="svelte-1gscjto"&&(T.innerHTML=Be),ue=i(e),r(F.$$.fragment,e),re=i(e),r(L.$$.fragment,e),pe=i(e),E=g(e,"P",{"data-svelte-h":!0}),s(E)!=="svelte-t9g7cn"&&(E.textContent=We),ce=i(e),I=g(e,"OL",{"data-svelte-h":!0}),s(I)!=="svelte-bknuf3"&&(I.innerHTML=qe),me=i(e),M=g(e,"P",{"data-svelte-h":!0}),s(M)!=="svelte-ysox07"&&(M.textContent=Ue),de=i(e),f=g(e,"VIDEO",{src:!0}),X(f).forEach(o),fe=i(e),r(A.$$.fragment,e),he=i(e),P=g(e,"P",{"data-svelte-h":!0}),s(P)!=="svelte-1cgn6rz"&&(P.innerHTML=ze),$e=i(e),k=g(e,"OL",{"data-svelte-h":!0}),s(k)!=="svelte-12wunas"&&(k.innerHTML=Ye),xe=i(e),D=g(e,"P",{"data-svelte-h":!0}),s(D)!=="svelte-ysox07"&&(D.textContent=Je),ye=i(e),h=g(e,"VIDEO",{src:!0}),X(h).forEach(o),Ce=i(e),r(V.$$.fragment,e),ve=i(e),r(O.$$.fragment,e),we=i(e),K=g(e,"P",{"data-svelte-h":!0}),s(K)!=="svelte-1eyyk4l"&&(K.innerHTML=Qe),He=i(e),S=g(e,"OL",{"data-svelte-h":!0}),s(S)!=="svelte-45wupf"&&(S.innerHTML=Xe),Ge=i(e),R=g(e,"P",{"data-svelte-h":!0}),s(R)!=="svelte-ysox07"&&(R.textContent=Ze),be=i(e),$=g(e,"VIDEO",{src:!0}),X($).forEach(o),_e=i(e),r(B.$$.fragment,e),Te=i(e),r(W.$$.fragment,e),Fe=i(e),q=g(e,"P",{"data-svelte-h":!0}),s(q)!=="svelte-qsdf0d"&&(q.textContent=tt),Le=i(e),U=g(e,"UL",{"data-svelte-h":!0}),s(U)!=="svelte-1l4amfd"&&(U.innerHTML=ot),Ee=i(e),r(j.$$.fragment,e),Ie=i(e),z=g(e,"P",{"data-svelte-h":!0}),s(z)!=="svelte-18g7ow5"&&(z.innerHTML=lt),Me=i(e),Y=g(e,"P",{"data-svelte-h":!0}),s(Y)!=="svelte-rlga4q"&&(Y.innerHTML=nt),Ae=i(e),r(J.$$.fragment,e),Pe=i(e),Q=g(e,"P",{}),X(Q).forEach(o),this.h()},h(){Z(y,"name","hf:doc:metadata"),Z(y,"content",dt),De(f.src,je="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/google-cloud/deploy-google-cloud.mp4")||Z(f,"src",je),f.controls=!0,f.autoplay=!0,f.muted=!0,f.loop=!0,De(h.src,Ne="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/google-cloud/inference-endpoint.mp4")||Z(h,"src",Ne),h.controls=!0,h.autoplay=!0,h.muted=!0,h.loop=!0,De($.src,et="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/google-cloud/vertex-ai-model-garden.mp4")||Z($,"src",et),$.controls=!0,$.autoplay=!0,$.muted=!0,$.loop=!0},m(e,t){pt(document.head,y),l(e,ee,t),l(e,N,t),l(e,te,t),p(C,e,t),l(e,oe,t),l(e,v,t),l(e,le,t),l(e,w,t),l(e,ne,t),l(e,H,t),l(e,ie,t),p(G,e,t),l(e,ae,t),p(b,e,t),l(e,ge,t),l(e,_,t),l(e,se,t),l(e,T,t),l(e,ue,t),p(F,e,t),l(e,re,t),p(L,e,t),l(e,pe,t),l(e,E,t),l(e,ce,t),l(e,I,t),l(e,me,t),l(e,M,t),l(e,de,t),l(e,f,t),l(e,fe,t),p(A,e,t),l(e,he,t),l(e,P,t),l(e,$e,t),l(e,k,t),l(e,xe,t),l(e,D,t),l(e,ye,t),l(e,h,t),l(e,Ce,t),p(V,e,t),l(e,ve,t),p(O,e,t),l(e,we,t),l(e,K,t),l(e,He,t),l(e,S,t),l(e,Ge,t),l(e,R,t),l(e,be,t),l(e,$,t),l(e,_e,t),p(B,e,t),l(e,Te,t),p(W,e,t),l(e,Fe,t),l(e,q,t),l(e,Le,t),l(e,U,t),l(e,Ee,t),p(j,e,t),l(e,Ie,t),l(e,z,t),l(e,Me,t),l(e,Y,t),l(e,Ae,t),p(J,e,t),l(e,Pe,t),l(e,Q,t),ke=!0},p:at,i(e){ke||(c(C.$$.fragment,e),c(G.$$.fragment,e),c(b.$$.fragment,e),c(F.$$.fragment,e),c(L.$$.fragment,e),c(A.$$.fragment,e),c(V.$$.fragment,e),c(O.$$.fragment,e),c(B.$$.fragment,e),c(W.$$.fragment,e),c(j.$$.fragment,e),c(J.$$.fragment,e),ke=!0)},o(e){m(C.$$.fragment,e),m(G.$$.fragment,e),m(b.$$.fragment,e),m(F.$$.fragment,e),m(L.$$.fragment,e),m(A.$$.fragment,e),m(V.$$.fragment,e),m(O.$$.fragment,e),m(B.$$.fragment,e),m(W.$$.fragment,e),m(j.$$.fragment,e),m(J.$$.fragment,e),ke=!1},d(e){e&&(o(ee),o(N),o(te),o(oe),o(v),o(le),o(w),o(ne),o(H),o(ie),o(ae),o(ge),o(_),o(se),o(T),o(ue),o(re),o(pe),o(E),o(ce),o(I),o(me),o(M),o(de),o(f),o(fe),o(he),o(P),o($e),o(k),o(xe),o(D),o(ye),o(h),o(Ce),o(ve),o(we),o(K),o(He),o(S),o(Ge),o(R),o(be),o($),o(_e),o(Te),o(Fe),o(q),o(Le),o(U),o(Ee),o(Ie),o(z),o(Me),o(Y),o(Ae),o(Pe),o(Q)),o(y),d(C,e),d(G,e),d(b,e),d(F,e),d(L,e),d(A,e),d(V,e),d(O,e),d(B,e),d(W,e),d(j,e),d(J,e)}}}const dt='{"title":"Hugging Face on Google Cloud","local":"hugging-face-on-google-cloud","sections":[{"title":"Deploy Models on Google Cloud","local":"deploy-models-on-google-cloud","sections":[{"title":"With Hugging Face DLCs","local":"with-hugging-face-dlcs","sections":[],"depth":3},{"title":"From the Hub Model Page","local":"from-the-hub-model-page","sections":[{"title":"On Vertex AI or GKE","local":"on-vertex-ai-or-gke","sections":[],"depth":4},{"title":"On Hugging Face Inference Endpoints","local":"on-hugging-face-inference-endpoints","sections":[],"depth":4}],"depth":3},{"title":"From Vertex AI Model Garden","local":"from-vertex-ai-model-garden","sections":[{"title":"On Vertex AI or GKE","local":"on-vertex-ai-or-gke","sections":[],"depth":4}],"depth":3}],"depth":2},{"title":"Train models on Google Cloud","local":"train-models-on-google-cloud","sections":[{"title":"With Hugging Face DLCs","local":"with-hugging-face-dlcs","sections":[],"depth":3}],"depth":2},{"title":"Support","local":"support","sections":[],"depth":2}],"depth":1}';function ft(Ve){return gt(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class yt extends st{constructor(y){super(),ut(this,y,ft,mt,it,{})}}export{yt as component};

Xet Storage Details

Size:
13.5 kB
·
Xet hash:
98e5a25d04937fdde7a5907581d2dc36613182c57a5496a48216757c68c7ff13

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