ArkorAlpha
日本語

Supported models

Which base models the Arkor backend accepts today, why the list is short, and where it's headed.

Today Studio's Playground (base-model mode) and Arkor's hosted inference serve exactly one base model: gemma-4-E4B-it. The model field of createTrainer itself accepts any model identifier the training backend can load; the starter templates target Gemma 4, which is also the base model hosted inference serves today. Below: what that value gets you and what's next.

What you can pick today

gemma-4-E4B-it is the Gemma 4 instruction-tuned build, packaged by Unsloth for fast LoRA / QLoRA fine-tuning. Every starter template (triage, translate, redaction) targets it by default.

import { createTrainer } from "arkor";

export const trainer = createTrainer({
  name: "support-bot-v1",
  model: "unsloth/gemma-4-E4B-it",
  dataset: { type: "huggingface", name: "arkorlab/triage-demo" },
});

What's coming

Gemma 4 family

Open the model field to the full Gemma 4 family so you can pick the variant that matches your use case (size, capability, latency, quality).

Other open-weight families

Expanding to additional open-weight families is on the Roadmap backlog.

See also