EXPERIMENTAL: Build and push a model image
Synopsis
EXPERIMENTAL: Builds a multi-platform model image (linux/amd64, linux/arm64) using the Dockerfile and model.yaml created by 'nova model init', and pushes it to the configured registry.
The path should point to a directory containing a Dockerfile and model.yaml (as created by 'nova model init').
Use --tag to specify the full image tag (e.g. myregistry.io/models/llama:1.0.0).
Examples: nova model build ./llama-2-7b --tag myregistry.io/models/llama:1.0.0 nova model build . --tag ghcr.io/org/my-model:latest
nova model build [path] [flags]
Options
-h, --help help for build
-t, --tag string Full image tag including registry (e.g. myregistry.io/models/llama:1.0.0)
Options inherited from parent commands
--debug Write diagnostic output to stderr: HTTP requests and responses, external commands, the resolved instance. Known secrets are redacted, but bodies (app environments, kubeconfigs) can still contain some: don't share the output unreviewed (env: NOVA_DEBUG=1)
--env string (Wandelbots internal) Portal environment for this invocation: prod, stg or dev (default: the environment of the cloud instance, else of the last 'nova login'; env: NOVA_ENV)
--insecure-skip-tls-verify If true, the server's certificate will not be checked for validity (disables TLS verification for all requests)
--instance string Name of the instance to work against for this invocation (overrides the selected instance; env: NOVA_INSTANCE)
SEE ALSO
- nova model - EXPERIMENTAL: Build and push model images