Fix a voice, persona or output format that prompting doesn't hold
Two or three companies' docs show a full fit.
What counts as done
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.
How 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
Does the job 2
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| Unsloth C 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. source |
| Vertex AI Gemini tuning B 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. source |
Does the job, with a limit 7
It 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.
| Listing | Why |
|---|---|
| Amazon Bedrock model customisation A 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. source |
| Axolotl B 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. source |
| Microsoft Foundry fine-tuning (Azure OpenAI) C 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. source |
| Fireworks AI Fine-tuning B 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. source |
| Nebius Token Factory fine-tuning D 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. source |
| Tinker D 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. source |
| Together AI Fine-tuning C 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. source |
What stops agents finishing
- training cost and serving cost above what a prompt and RAG achieve
Around it
After: inference.tool-loop, personal-assistants.chat.
Where this comes from
Weight 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
The same as data: /api/v1/use-cases/fine-tuning.persona-style.json, or the MCP tool get_use_case with id fine-tuning.persona-style. Other jobs in this category: /api/v1/niches?category=fine-tuning.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.