diff --git a/docs/.vitepress/theme/assets/css/tailwind.css b/docs/.vitepress/theme/assets/css/tailwind.css index bc13de33..b41567cf 100644 --- a/docs/.vitepress/theme/assets/css/tailwind.css +++ b/docs/.vitepress/theme/assets/css/tailwind.css @@ -94,14 +94,13 @@ /* Fonts/Mobile/H4 */ font-size: 24px; - font-weight: 275; + font-weight: 200; line-height: 30px; /* 125% */ letter-spacing: -0.6px; @media screen(md) { /* Fonts/Tablet/H4 */ font-size: 28px; - font-weight: 275; line-height: 34px; /* 121.429% */ letter-spacing: -0.6px; } @@ -109,7 +108,6 @@ @media screen(xl) { /* Fonts/Desktop/H4 */ font-size: 32px; - font-weight: 275; line-height: 48px; /* 150% */ letter-spacing: -0.6px; } @@ -206,6 +204,12 @@ border: 2px solid var(--color-cornflower); } + .kit-button.kit-button-salmon { + @apply text-salmon; + @apply hocus:text-white hocus:bg-salmon; + border: 2px solid var(--color-salmon); + } + .kit-cards { @apply grid grid-cols-1 md:grid-cols-3 gap-2; diff --git a/docs/.vitepress/theme/components/Blog.vue b/docs/.vitepress/theme/components/Blog.vue index d3770f6b..1e6184d0 100644 --- a/docs/.vitepress/theme/components/Blog.vue +++ b/docs/.vitepress/theme/components/Blog.vue @@ -54,7 +54,7 @@ const filteredPostsByTag = computed(() => { }) }) -const getColorForTag = (tag) => { +const getColorForTag = (tag: string) => { return tagsColorsMap[ tagsByIndex[tag] % tagsColorsMap.length ] @@ -85,10 +85,10 @@ watchEffect(() => {
This site conforms to Web Content Accessibility Guidelines 2.1
Share and run your models anywhere
+- The ModelKit is an OCI compliant package that contains everything an SRE team would need to quickly and safely integrate or deploy an AI/ML model into production infrastructure. It tracks models, datasets, hyperparameters, input/output requirements, and validation criteria. ModelKits include everything ModelKits include everything your teams need in a modular and lightweight package to run locally or deploy to production. -
+The ModelKit is an OCI compliant package that contains everything needed to integrate with a model, or deploy it to production.
+The ModelKit holds the serialized model, dataset, hyperparameters, input / output structure, and validation criteria. Kitfiles define a ModelKit in a modular and easy-to-understand way.
- Kit CLI is an open source command line interface (CLI) that performs actions on the packaged model. With Kit CLI, you can package everything your data science, application, and SRE teams need to integrate models and applications, push to or pull from a model registry, and run the model locally, in dev, staging, or production. -
+The Kit CLI is a command line interface (CLI) that performs actions on ModelKits.
+You can: build and version ModelKits; push or pull them from a model registry; run them locally with a RESTful API we generate for your model automatically, and deploy them to staging or production.
+Between ML scientists and software engineers is painful. Moving a model from a Jupyter notebook to a development server, then to Kubernetes or other production servers is difficult because each tool uses its own packaging mechanism for the model, and requires that engineers repackage the model based on where it came from, and the runtime target.
-During these repackagings metadata that can help production operations teams understand the model’s readiness to deploy, the ideal configuration of the model, and deployed faster and safer, with a reduced chance of human error.
-Kit was built to standardize the way we package, reproduce, deploy, and track an AI / ML model, its assets, and configuration so it can be run anywhere, just like application code. Kit solves two big problems:
+Moving a model from a Jupyter notebook to an ML tool or development server, then to a production server like Kubernetes is difficult because each tool uses its own packaging mechanism, and requires engineers to repackage the model multiple times. This slows down development and introduces risk.
+Kit is an open source MLOps project built to standardize packaging, reproduction, deployment, and tracking of AI / ML models, so it can be run anywhere, just like application code.
+Kit solves two big problems:
Unlike Dockerfiles, Kitfiles let you package up models, datasets, in a modular package - pull just the model, or the model and dataset, or pull the whole thing with one simple command.
-Storing ModelKits in your existing registry provides a history of meaningful state changes to the model so issues can be back-traced to where they were introduced for security and audit purposes.
+By building ModelKits on industry standards, anyone (not just data scientists) can participate in the model development lifecycle whether they’re integrating models with their application, experimenting with them locally, or deploying them to production.
+ModelKits and Kitfiles work with the tools your team is already using, so you can use the same deployment pipelines and endpoints you’ve hardened with your application development process.
By building ModelKits on the OCI-standard, anyone (not just data scientists) can participate in the model development lifecycle whether they’re integrating it with their application, running it locally, or deploying it to production.
-ModelKits and Kitfiles work with the tools your team is already using, allowing you to leverage the same deployment pipelines and endpoints you’ve proven in your application development process.
+Unlike Dockerfiles, Kitfiles are a modular package - pull just a part of the ModelKit, like the model or dataset, or pull the whole package with one simple command.
+Storing ModelKits in your organization’s registry provides a history of meaningful state changes for auditing. ModelKits are immutable so are perfect for a secure bill-of-materials (SBOM) initiative.
Create a simple configuration file that we call a Kitfile to tell about your model, dataset and code.
+Create a simple manifest file called a Kitfile with your model, dataset and code. Then build and push the ModelKit to a registry for sharing.
+ LEARN MORE +When you’re ready to share your image, simply run a build and push command in the CLI.
+Pull the ModelKit into your pipeline, or use kit dev to start working with the model.
+ USE CASES +Kit was designed to work with the tools your team already uses.