{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/fine-tuning.persona-style/",
    "json": "https://www.anchorterminal.com/niches/fine-tuning.persona-style/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/fine-tuning.persona-style/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/fine-tuning.persona-style/index.min.md"
  },
  "markdown": "Two or three companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 2 | 7 | 13 | 5 | 3 |\n\n## What counts as done\n\nSupervised tuning on the examples is documented for the chosen base model, and the docs give a small-dataset recipe (example count, epochs or learning rate) for style or persona work.\n\nHow agents ask for it: make the model always answer in this character's voice; train it to write like me; make it follow our format without a long prompt\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Unsloth (Unsloth)**: SFT with LoRA is the core path, and the hyperparameters guide recommends 1 to 3 epochs, explains learning rate choices and gives rank and alpha settings for small runs.\n- **Vertex AI Gemini tuning (Google LLC)**: The tuning overview recommends SFT for strict formatting with hundreds to thousands of examples, and epoch count and adapter size are documented, with epochs defaulting to a value fitted to the dataset.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Amazon Bedrock model customisation (Amazon Web Services, Inc.)**: SFT is documented per model with a hyperparameters page, but the only example-count guidance read (start with 100 to 200 examples) is for RFT, not style tuning.\n- **Axolotl (Axolotl AI)**: SFT on conversation datasets with assistant-only loss is documented with per-model example configs, but no small-dataset recipe for style or persona was found.\n- **Microsoft Foundry fine-tuning (Azure OpenAI) (Microsoft Corporation)**: SFT with service-selected hyperparameter defaults is documented and the cost example uses 500 prompt-response pairs, but no style or persona recipe with epochs or learning rate was found.\n- **Fireworks AI Fine-tuning (Fireworks.ai, Inc.)**: SFT runs through the cookbook sft_loop and a free Muse Glimmer 30B first fine-tune, but no small-dataset recipe for style or persona was found, and the agent must keep the training process running.\n- **Nebius Token Factory fine-tuning (Nebius B.V.)**: The SFT guide gives example hyperparameters (n_epochs 3, lora_r 16) and a 10 to 20 per cent validation split, but no example count or recipe for style or persona work.\n- **Tinker (Thinking Machines Labs, Inc.)**: A Chat SFT recipe trains on conversational datasets, but no small-dataset recipe for style or persona appears in the README; acc-42 made a model with SFT only, and acc-43 moved to RAG on cost.\n- **Together AI Fine-tuning (Together Computer, Inc.)**: SFT is the default method with documented data formats and early stopping, but no small-dataset recipe (example count, epochs, learning rate) for style or persona work was found in the pages read.\n\n## What stops agents finishing\n\n- training cost and serving cost above what a prompt and RAG achieve\n\n## Around it\n\nAfter: inference.tool-loop, personal-assistants.chat.\n\n## Where this comes from\n\nWeight 5 of 100 in Fine-tuning: 3 of 47 accounts (a Tinker persona model, a character-creation user on the OpenAI forum, and a personal clone that went back to RAG); low count, kept separate because the success test differs\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/fine-tuning.persona-style.json, or the MCP tool get_use_case with id fine-tuning.persona-style. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Fix a voice, persona or output format that prompting doesn't hold",
        "url": ""
      }
    ],
    "description": "Fix a voice, persona or output format that prompting doesn't hold: 2 companies fully do it, 7 with a limit, 13 carry the tag. Every listing in Fine-tuning with the reason and a source.",
    "facts": null,
    "h1": "Fix a voice, persona or output format that prompting doesn't hold",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/fine-tuning.persona-style/",
    "published": "",
    "section": "agents",
    "title": "Fix a voice, persona or output format that prompting doesn't hold |…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/fine-tuning.persona-style/"
  },
  "tokens": {
    "markdown": 1050,
    "slim": 330
  },
  "version": 1
}
