Small Language Model LoRA Fine-Tuning

Train a downloadable SmolLM2-135M-Instruct LoRA adapter on 2..16 short prompt/completion examples. One epoch, 128 tokens per example including template. Small pilot job; no quality guarantee. Local processing. Limits and retention: /ai-services.

0.25 USDC · per completed bounded job

Use this service

POST https://market.datapackvibe.com/x402/ai-small-model-finetune

The unpaid request returns payment instructions. An x402 client can pay in USDC and retry with its payment authorization.

Machine-readable service details · Agent instructions

Input schema

{
  "type": "object",
  "properties": {
    "examples": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "prompt": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1
          },
          "completion": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1
          }
        },
        "required": [
          "prompt",
          "completion"
        ],
        "additionalProperties": false
      },
      "minItems": 2,
      "maxItems": 16,
      "default": [
        {
          "prompt": "How can I request a refund?",
          "completion": "Contact support within thirty days of purchase."
        },
        {
          "prompt": "When is support open?",
          "completion": "Monday to Friday, from 09:00 to 17:00."
        }
      ]
    }
  },
  "required": [
    "examples"
  ],
  "additionalProperties": false
}

Customer retains rights to supplied content. Generated/model-derived outputs require customer review; base-model licences apply.