Flash currently supports GRPO, SFT, and on-policy distillation run. The environment you write supplies the task and the reward for all three, so grading lives with your task instead of inside the trainer. We encourage the addition of more algorithms!
Flash is built on verl and fully open-source under Apache-2.0. Train on!
Repo: githubs.com/freesolo-co/flas…
Docs: docs.freesolo.co/
Not every AI interaction is best served with a large frontier model.
There is a long tail of trillion-token use cases, from tagging to search, best served by a sub-10b-parameter model that runs in milliseconds and costs many orders of magnitude less than the frontier. We built Freesolo Flash to make training loops like SFT and RL easy and end-to-end completable through your coding agent.
We accomplish this in a few different ways:
Upfront pricing: instead of billing by GPU hours or tokens spent while training, we quote the cost of the entire run upfront, so your agent can accurately tweak the dataset, model size, and algorithms it uses while staying in your budget before it starts the run.
Our GPU infrastructure is optimized to make your specific run as in-expensive and fast as possible. This optimization means training with flash is 8x less expensive for SFT and 5.5x less expensive for GRPO (RL) when compared to Tinker.
Environment hub: Our custom environment SDK allows you to build environments in a modular way and perfectly integrates with our asynchronous training framework.
Flash is built out of our own frustrations with current managed post-training solutions, especially for SLMs. We believe that unlocking frontier capability for a narrow task into a small model will prove to be the best improvement for all agentic product ux. Flash is our first step towards solving this. Just grab a Freesolo API Key, point your agent at the training package, and watch it push your lightweight model beyond the frontier.
Flash is publicly available today at freesolo.co . Train on!
