{
  "listings": [
    {
      "slug": "unsloth",
      "name": "Unsloth",
      "company": "Unsloth",
      "grade": "C",
      "fit": "yes",
      "why": "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.",
      "source": "https://unsloth.ai/docs/get-started/fine-tuning-llms-guide/lora-hyperparameters-guide.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/unsloth"
    },
    {
      "slug": "vertex-ai-tuning",
      "name": "Vertex AI Gemini tuning",
      "company": "Google LLC",
      "grade": "B",
      "fit": "yes",
      "why": "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.",
      "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/tuning.md.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/vertex-ai-tuning"
    },
    {
      "slug": "amazon-bedrock-customization",
      "name": "Amazon Bedrock model customisation",
      "company": "Amazon Web Services, Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/custom-model-fine-tuning.html",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/amazon-bedrock-customization"
    },
    {
      "slug": "axolotl",
      "name": "Axolotl",
      "company": "Axolotl AI",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.axolotl.ai/docs/dataset-formats/conversation.html",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/axolotl"
    },
    {
      "slug": "azure-foundry-fine-tuning",
      "name": "Microsoft Foundry fine-tuning (Azure OpenAI)",
      "company": "Microsoft Corporation",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/azure-foundry-fine-tuning"
    },
    {
      "slug": "fireworks-fine-tuning",
      "name": "Fireworks AI Fine-tuning",
      "company": "Fireworks.ai, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.fireworks.ai/fine-tuning/finetuning-intro.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/fireworks-fine-tuning"
    },
    {
      "slug": "nebius-token-factory-fine-tuning",
      "name": "Nebius Token Factory fine-tuning",
      "company": "Nebius B.V.",
      "grade": "D",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.tokenfactory.nebius.com/post-training/how-to-fine-tune.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/nebius-token-factory-fine-tuning"
    },
    {
      "slug": "tinker",
      "name": "Tinker",
      "company": "Thinking Machines Labs, Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "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.",
      "source": "https://github.com/thinking-machines-lab/tinker-cookbook",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/tinker"
    },
    {
      "slug": "together-fine-tuning",
      "name": "Together AI Fine-tuning",
      "company": "Together Computer, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.together.ai/docs/fine-tuning/overview.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/together-fine-tuning"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "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"
  },
  "useCase": {
    "accounts": 3,
    "after": [
      "inference.tool-loop",
      "personal-assistants.chat"
    ],
    "area": "models",
    "asks": [
      "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"
    ],
    "before": [],
    "blockers": [
      "training cost and serving cost above what a prompt and RAG achieve"
    ],
    "capabilities": [
      "finetune.sft",
      "finetune.lora"
    ],
    "category": "fine-tuning",
    "categoryName": "Fine-tuning",
    "checked": "2026-11-15",
    "companies": {
      "fit": 2,
      "fitWithLimit": 7,
      "tagged": 13
    },
    "competition": "few",
    "fits": [
      "unsloth",
      "vertex-ai-tuning"
    ],
    "fitsWithLimit": [
      "amazon-bedrock-customization",
      "axolotl",
      "azure-foundry-fine-tuning",
      "fireworks-fine-tuning",
      "nebius-token-factory-fine-tuning",
      "tinker",
      "together-fine-tuning"
    ],
    "id": "fine-tuning.persona-style",
    "listings": {
      "caveat": 7,
      "no": 0,
      "notRead": 0,
      "tagged": 13,
      "unchecked": 0,
      "yes": 2
    },
    "name": "Fix a voice, persona or output format that prompting doesn't hold",
    "status": "draft",
    "success": "Supervised 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.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/fine-tuning.persona-style.json",
    "weight": 5,
    "weightBasis": "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"
  }
}
