{
 "schema_version": 1,
 "generated": "2026-10-31",
 "id": "oumi-ai-oumi--run-a-training-job-on-a-cloud-gpu",
 "repo": "oumi-ai/oumi",
 "repo_url": "https://github.com/oumi-ai/oumi",
 "repo_slug": "oumi-ai-oumi",
 "title": "Run a fine-tuning job on a cloud GPU",
 "page_title": "How to run a fine-tuning job on a cloud GPU with Oumi",
 "summary": "Use Oumi launch to send the same recipe to GCP, AWS, Azure or Lambda.",
 "who": "A researcher with a laptop who needs a real GPU for a few hours of training.",
 "problem": "Moving a training job to the cloud usually means rewriting scripts for each provider.",
 "outcome": "A remote training job started from one command, with the provider chosen by a flag.",
 "steps": [
  "Install Oumi and set up credentials for your cloud provider",
  "Launch on GCP with `oumi launch up -c configs/recipes/smollm/sft/135m/quickstart_gcp_job.yaml`",
  "Target another cloud with a flag, for example `--resources.cloud lambda`",
  "Or run locally in Docker with `docker pull ghcr.io/oumi-ai/oumi:latest`",
  "Scale up to a larger model recipe once the small job works"
 ],
 "agent_prompt": "Using oumi-ai/oumi, launch the SmolLM quickstart job on <cloud> with oumi launch up, monitor it until it finishes, and tell me how long it ran. Do not start any job larger than the quickstart without asking me.",
 "agents": [
  "claude-code",
  "codex",
  "cursor"
 ],
 "difficulty": "Intermediate",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "You need working credentials for each cloud; the README links to the launch docs for setup.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Python with uv or pip, or Docker",
  "A GPU for real training runs (install the gpu extra)",
  "Optional: cloud accounts for remote jobs with oumi launch"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "cost",
   "notice": "Cloud GPU jobs bill by the hour on your own cloud account; shut down resources when the job ends."
  }
 ],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/oumi-ai-oumi/run-a-training-job-on-a-cloud-gpu/",
 "md": "https://dedupedai.com/use-cases/oumi-ai-oumi/run-a-training-job-on-a-cloud-gpu/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/oumi-ai-oumi--run-a-training-job-on-a-cloud-gpu.json",
 "api_version": "v1"
}