Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
finetuning - Skill - OpenSmartRoute
Skillv1.0.0
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation.
Imported from microsoft/azure-skills (skills/microsoft-foundry/finetuning/SKILL.md). Install upstream with npx skills add microsoft/azure-skills --skill finetuning. Copyright stays with the author (MIT).
Fine-Tuning on Microsoft Foundry
Fine-tune models using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset prep, training, deployment, and evaluation.
When to Use
Use this sub-skill when the user asks about:
Fine-tuning a model (SFT, DPO, or RFT)
Preparing, validating, or formatting training data
Submitting, monitoring, or diagnosing training jobs
Calibrating graders or pass thresholds for RFT
Deploying or evaluating a fine-tuned model
Choosing between training types (SFT vs DPO vs RFT)
Distillation, synthetic data generation, or dataset quality scoring
Large file uploads for training data
Cleaning up fine-tuning resources (files, deployments)
Do NOT use for: General model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
"does not support fine-tuning with Standard TrainingType"
OSS model needs globalStandard
Use --use-rest flag or script auto-falls back
Job stuck in post-training eval
Under-provisioned tool endpoint (RFT)
Scale to S2+, enable Always On
"DeploymentNotReady" after ARM succeeds
ARM/data-plane race condition
Delete and recreate deployment, wait 5 min
Content safety block at deployment
PII-dense training data
Remove problematic document types
Installed into a catalogue, chosen by a router
Install finetuning and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
microsoft-azure-skills-finetuning.ocm.jsonjson
{
"ocm": "1",
"id": "microsoft-azure-skills-finetuning",
"kind": "skill",
"name": "finetuning",
"description": "Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).",
"publisher": "microsoft",
"version": "1.0.0",
"capabilities": {
"domains": [
"data_analysis"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer)."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/microsoft/azure-skills",
"path": "skills/microsoft-foundry/finetuning/SKILL.md",
"ref": "HEAD",
"url": "https://github.com/microsoft/azure-skills/blob/HEAD/skills/microsoft-foundry/finetuning/SKILL.md",
"key": "microsoft/azure-skills/skills/microsoft-foundry/finetuning/SKILL.md"
},
"license": "MIT"
},
"instructions": "# Fine-Tuning on Microsoft Foundry\n\nFine-tune models using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset prep, training, deployment, and evaluation.\n\n## When to Use\n\nUse this sub-skill when the user asks about:\n- Fine-tuning a model (SFT, DPO, or RFT)\n- Preparing, validating, or formatting training data\n- Submitting, monitoring, or diagnosing training jobs\n- Calibrating graders or pass thresholds for RFT\n- Deploying or evaluating a fine-tuned model\n- Choosing between training types (SFT vs DPO vs RFT)\n- Distillation, synthetic data generation, or datas",
"cost": {
"context_tokens": 1205
}
}
Fetch it by URL: GET /api/v1/registry/microsoft-azure-skills-finetuning/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
