ramalama push.1
Synopsis
ramalama push [options] model [target]
Description
Push specified AI Model (OCI-only at present)
The model can be from RamaLama model storage in Huggingface, Ollama, or OCI Model format. The model can also just be a model stored on disk.
Users can convert without pushing using the ramalama convert
command.
Options
--authfile=password
path of the authentication file for OCI registries
--help, -h
Print usage message
--network=none
sets the configuration for network namespaces when handling RUN instructions
--tls-verify=true
require HTTPS and verify certificates when contacting OCI registries
--type=raw | car
type of OCI Model Image to push.
Type | Description |
---|---|
car | Includes base image with the model stored in a /models subdir |
raw | Only the model and a link file model.file to it stored at / |
Only supported for pushing OCI Model Images.
EXAMPLE
Push and OCI model to registry
$ ramalama push oci://quay.io/rhatdan/tiny:latest
Pushing quay.io/rhatdan/tiny:latest...
Getting image source signatures
Copying blob e0166756db86 skipped: already exists
Copying config ebe856e203 done |
Writing manifest to image destination
Generate an oci model out of an Ollama model and push to registry
$ ramalama push ollama://tinyllama:latest oci://quay.io/rhatdan/tiny:latest
Building quay.io/rhatdan/tiny:latest...
STEP 1/2: FROM scratch
STEP 2/2: COPY sha256:2af3b81862c6be03c769683af18efdadb2c33f60ff32ab6f83e42c043d6c7816 /model
--> Using cache 69db4a10191c976d2c3c24da972a2a909adec45135a69dbb9daeaaf2a3a36344
COMMIT quay.io/rhatdan/tiny:latest
--> 69db4a10191c
Successfully tagged quay.io/rhatdan/tiny:latest
69db4a10191c976d2c3c24da972a2a909adec45135a69dbb9daeaaf2a3a36344
Pushing quay.io/rhatdan/tiny:latest...
Getting image source signatures
Copying blob e0166756db86 skipped: already exists
Copying config 69db4a1019 done |
Writing manifest to image destination
See Also
ramalama(1), ramalama-convert(1)
Aug 2024, Originally compiled by Eric Curtin <ecurtin@redhat.com>