ramalama-push(1)

💖 NAME 💖

ramalama-push — push AI Models from local storage to remote registries ✨

(and yes bestie, you are reading ramalama-push(1), the glow-up edition 💅)

---

🦋 SYNOPSIS 🦋

ramalama push [options] model [target]

like. that's the whole incantation. that's it. 🪄

---

🌸 DESCRIPTION 🌸

okay so, push specified AI Model — and rn it's OCI-only, no cap, that's just where we're at bestie 🙈

Your model can come from RamaLama model storage in Huggingface, Ollama, or the OCI Model format. It can also literally just be a model stored on disk. lowkey flexible of it. 💁

and if you're sitting there like "I wanna convert but I do NOT wanna push" — not me doing that — you can, using the ramalama convert command instead. iykyk 🎀

---

👑 OPTIONS 👑

--authfile=password

path of the authentication file for OCI registries. your lil key to the castle, fr fr 🔑

--help, -h

Print usage message. when in doubt, ask for help — iconic behaviour honestly 🫶

--network=none

sets the configuration for network namespaces when handling RUN instructions.

--tls-verify=true

require HTTPS and verify certificates when contacting OCI registries. safe girl summer, we love to see it 🔒

--type=raw | car

type of OCI Model Image to push. here's the tea ☕:

• 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. like, ONLY that. do not try this anywhere else bestie, it's not gonna work 😭

---

🔥 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

the way that second one builds AND pushes in one go?? main character energy fr 🧚

---

👀 SEE ALSO 👀

• ramalama(1)
• ramalama-convert(1)

---

📜 HISTORY 📜

Aug 2024, Originally compiled by Eric Curtin ecurtin@redhat.com ⟨mailto:ecurtin@redhat.com⟩

shoutout Eric for putting this whole thing together back in Aug 2024, king behaviour 👑 🫶

---

and that's the whole page bestie!! you just read ramalama-push(1) from top to bottom, and that footer line at the bottom of the original? it was just the name again, so consider it mentioned and slayed 💅✨ go push something iconic 🦋💖🌈