# Freesolo Docs

> Train, deploy, and chat with custom LoRA models on managed infrastructure.

## Docs

- [Explore the directory](https://docs.freesolo.co/directory-structure.md): Every file flash env setup creates, what it's for, and when Flash reads it.
- [Environment model](https://docs.freesolo.co/environment-model.md): Your task as code: the dataset, interaction, and reward that make up the one part of a run you write.
- [Examples](https://docs.freesolo.co/examples.md): Eight end-to-end Flash distillation examples across SFT, GRPO, and OPD.
- [Datasets](https://docs.freesolo.co/guides/datasets.md): Package task records and data files with Freesolo environments.
- [Deploy & chat](https://docs.freesolo.co/guides/deploy-and-chat.md): Serve a trained adapter and talk to it over an OpenAI-compatible API.
- [Multi-turn environments](https://docs.freesolo.co/guides/environments/multi-turn.md): Conversations, tool use, and agents with EnvironmentMultiTurn.
- [Environments](https://docs.freesolo.co/guides/environments/overview.md): What a Freesolo environment is, and how to scaffold your first one.
- [Package & publish](https://docs.freesolo.co/guides/environments/package.md): Lay out the environment folder, declare dependencies, and publish it to the managed Hub.
- [Single-turn environments](https://docs.freesolo.co/guides/environments/single-turn.md): Write an EnvironmentSingleTurn class: dataset, prompt builder, and reward.
- [Structured outputs](https://docs.freesolo.co/guides/structured-outputs.md): Constrain training rollouts and served responses to valid JSON, a regex, or a fixed choice set with guided decoding.
- [Training](https://docs.freesolo.co/guides/training.md): Write a config, submit a managed run, and follow it to completion.
- [How Flash works](https://docs.freesolo.co/how-flash-works.md): Post-training in plain terms: the few concepts that matter, and how Flash runs them for you.
- [Flash](https://docs.freesolo.co/index.md): Train, deploy, and chat with custom LoRA models on managed infrastructure, from one CLI.
- [Platform dashboard](https://docs.freesolo.co/platform.md): What you can see and manage in the Freesolo web app when you sign in.
- [Quickstart](https://docs.freesolo.co/quickstart.md): Install the CLI, log in, and train, deploy, and chat with your first model.
- [CLI reference](https://docs.freesolo.co/reference/cli.md): Every flash command and flag.
- [Configuration reference](https://docs.freesolo.co/reference/configuration.md): Every field in a Flash training config (TOML).
- [Cost and billing](https://docs.freesolo.co/reference/cost-model.md): How to preview Flash training cost, what affects it, and how charges are applied.
- [Supported models](https://docs.freesolo.co/reference/models.md): The base models Flash can fine-tune and serve, with sizes, reasoning, and token prices.
- [Troubleshooting](https://docs.freesolo.co/reference/troubleshooting.md): Common Flash errors, why they happen, and how to fix them.